Prepare for hello joypad!

.gitignore

@@ -17,3 +17,5 @@ toolchain/PSn00bSDK
 .vscode/settings.json
 toolchain/lfs
 toolchain/lpeg
+
+scratch

.vscode/launch.json

@@ -138,7 +138,6 @@
 				"monitor reset shellhalt",
 				"load build/hello_gte.dwarf-injected.elf",
 				"source scripts/gdb/gdb_tape_atoms.gdb",
-				"source build/gen/hello_gte.gdbinit",
 				"tbreak main",
 				"continue"
 			]

code/duffle/gen/duffle.macs.h

@@ -98,11 +98,11 @@ WORD_COUNT(mac_format_f3_color, 3)
 /* atom_dbg_skip */
 /* Words: 3; Stores the 3 transformed (V2_S2 screen) vertices to the F3.
  * PIPELINE: post-RTPT (SXY0=v0.screen, SXY1=v1.screen, SXY2=v2.screen). */
-#define mac_gte_store_f3_post_rtpt(...) \
+#define mac_gte_store_f3(...) \
 	gte_sw(C2_SXY0, R_PrimCursor, O_(Poly_F3,p0)) \
 ,	gte_sw(C2_SXY1, R_PrimCursor, O_(Poly_F3,p1)) \
 ,	gte_sw(C2_SXY2, R_PrimCursor, O_(Poly_F3,p2))
-WORD_COUNT(mac_gte_store_f3_post_rtpt, 3)
+WORD_COUNT(mac_gte_store_f3, 3)
 
 #define mac_format_g4_color(r0, g0, b0, r1, g1, b1, r2, g2, b2, r3, g3, b3) \
 	mac_pack_color_word(O_(Poly_G4,c0), gp0_cmd_poly_g4, r0,g0,b0) \
@@ -115,25 +115,20 @@ WORD_COUNT(mac_format_g4_color, 12)
 /* Words: 3; Stores the 3 transformed (V2_S2 screen) vertices of the
  * G4 triangle portion to p0/p1/p2.
  * PIPELINE: post-RTPT, pre-RTPS (SXY0=v0.screen, SXY1=v1.screen, SXY2=v2.screen). 
- * MUST be called BEFORE V3-RTPS, otherwise SXY0/1/2
+ * MUST be called BEFORE V3-RTPS, otherwise SXY0/1/2 get overwritten with v3
- * get overwritten with v3 (RTPS writes only to SXY2, but to keep the
+ * (RTPS writes only to SXY2, but to keep the three registers aligned with v0/v1/v2 you must store before RTPS). */
- * three registers aligned with v0/v1/v2 you must store before RTPS).
+#define mac_gte_store_g4_p012(...) \
- * The macro name declares the pipeline position; check #6 (GTE state-
- * machine validation) verifies the call site matches the declaration. */
-#define mac_gte_store_g4_p012_post_rtpt_pre_rtps(...) \
 	gte_sw(C2_SXY0, R_PrimCursor, O_(Poly_G4,p0)) \
 ,	gte_sw(C2_SXY1, R_PrimCursor, O_(Poly_G4,p1)) \
 ,	gte_sw(C2_SXY2, R_PrimCursor, O_(Poly_G4,p2))
-WORD_COUNT(mac_gte_store_g4_p012_post_rtpt_pre_rtps, 3)
+WORD_COUNT(mac_gte_store_g4_p012, 3)
 
 /* atom_dbg_skip */
 /* Words: 1; Stores the V3 screen coord to the G4's p3 slot.
- * PIPELINE: post-RTPS (SXY2 holds v3.screen because RTPS writes its
+ * PIPELINE: post-RTPS (SXY2 holds v3.screen because RTPS writes its single-vertex result to SXY2;
- * single-vertex result to SXY2; SXY0 still holds v0.screen from the
+ * SXY0 still holds v0.screen from the earlier RTPT.
- * earlier RTPT — DO NOT read SXY0 here, that's the bug this name
- * prevents).
  */
-#define mac_gte_store_g4_p3_post_rtps(...) \
+#define mac_gte_store_g4_p3(...) \
 	gte_sw(C2_SXY2, R_PrimCursor, O_(Poly_G4,p3))
-WORD_COUNT(mac_gte_store_g4_p3_post_rtps, 1)
+WORD_COUNT(mac_gte_store_g4_p3, 1)
 

code/duffle/lottes_tape.h

@@ -170,7 +170,7 @@ atom_dbg_skip MipsAtomComp_Proc_(ac_format_f3_color, { mac_pack_color_word(O_(Po
 
 /* Words: 3; Stores the 3 transformed (V2_S2 screen) vertices to the F3.
  * PIPELINE: post-RTPT (SXY0=v0.screen, SXY1=v1.screen, SXY2=v2.screen). */
-atom_dbg_skip MipsAtomComp_(ac_gte_store_f3_post_rtpt) {
+atom_dbg_skip MipsAtomComp_(ac_gte_store_f3) {
 	gte_sw(C2_SXY0, R_PrimCursor, O_(Poly_F3,p0)),
 	gte_sw(C2_SXY1, R_PrimCursor, O_(Poly_F3,p1)),
 	gte_sw(C2_SXY2, R_PrimCursor, O_(Poly_F3,p2)),
@@ -193,24 +193,19 @@ MipsAtomComp_Proc_(ac_format_g4_color, {
 /* Words: 3; Stores the 3 transformed (V2_S2 screen) vertices of the
  * G4 triangle portion to p0/p1/p2.
  * PIPELINE: post-RTPT, pre-RTPS (SXY0=v0.screen, SXY1=v1.screen, SXY2=v2.screen). 
- * MUST be called BEFORE V3-RTPS, otherwise SXY0/1/2
+ * MUST be called BEFORE V3-RTPS, otherwise SXY0/1/2 get overwritten with v3
- * get overwritten with v3 (RTPS writes only to SXY2, but to keep the
+ * (RTPS writes only to SXY2, but to keep the three registers aligned with v0/v1/v2 you must store before RTPS). */
- * three registers aligned with v0/v1/v2 you must store before RTPS).
+atom_dbg_skip MipsAtomComp_(ac_gte_store_g4_p012) {
- * The macro name declares the pipeline position; check #6 (GTE state-
- * machine validation) verifies the call site matches the declaration. */
-atom_dbg_skip MipsAtomComp_(ac_gte_store_g4_p012_post_rtpt_pre_rtps) {
 	gte_sw(C2_SXY0, R_PrimCursor, O_(Poly_G4,p0)),
 	gte_sw(C2_SXY1, R_PrimCursor, O_(Poly_G4,p1)),
 	gte_sw(C2_SXY2, R_PrimCursor, O_(Poly_G4,p2)),
 };
 
 /* Words: 1; Stores the V3 screen coord to the G4's p3 slot.
- * PIPELINE: post-RTPS (SXY2 holds v3.screen because RTPS writes its
+ * PIPELINE: post-RTPS (SXY2 holds v3.screen because RTPS writes its single-vertex result to SXY2;
- * single-vertex result to SXY2; SXY0 still holds v0.screen from the
+ * SXY0 still holds v0.screen from the earlier RTPT.
- * earlier RTPT — DO NOT read SXY0 here, that's the bug this name
- * prevents).
  */
-atom_dbg_skip MipsAtomComp_(ac_gte_store_g4_p3_post_rtps) { gte_sw(C2_SXY2, R_PrimCursor, O_(Poly_G4,p3)) };
+atom_dbg_skip MipsAtomComp_(ac_gte_store_g4_p3) { gte_sw(C2_SXY2, R_PrimCursor, O_(Poly_G4,p3)) };
 
 #pragma endregion Macro Atom Components
 

code/hello_gte/gen/gte_hello.offsets.h

@@ -5,10 +5,10 @@
 #pragma region hello_gte_tape
 
 
-// --- atom: cube_g4_face (87 words) ---
+// --- atom: cube_g4_face (77 words) ---
 
-#define _atom_offset_cull_cube_g4_face_exit           48
+#define _atom_offset_cull_cube_g4_face_exit           42
-#define _atom_offset_bounds_chk_cube_g4_face_exit     12
+#define _atom_offset_bounds_chk_cube_g4_face_exit     24
 
 enum {
     atom_offset_cull_cube_g4_face_exit = _atom_offset_cull_cube_g4_face_exit,
@@ -18,7 +18,7 @@ enum {
 // --- atom: floor_f3_face (58 words) ---
 
 #define _atom_offset_culling_floor_f3_face_exit       25
-#define _atom_offset_bounds_chk_floor_f3_face_exit    13
+#define _atom_offset_bounds_chk_floor_f3_face_exit    16
 
 enum {
     atom_offset_culling_floor_f3_face_exit = _atom_offset_culling_floor_f3_face_exit,

code/hello_gte/gen/hello_gte.offsets.h

@@ -0,0 +1,29 @@
+// Auto-generated by ps1_meta.lua (passes/offsets.lua) — DO NOT EDIT
+// Source: C:\projects\Pikuma\ps1\code\hello_gte\hello_gte.tape.c
+#pragma once
+
+#pragma region hello_gte.tape
+
+
+// --- atom: cube_g4_face (77 words) ---
+
+#define _atom_offset_cull_cube_g4_face_exit           42
+#define _atom_offset_bounds_chk_cube_g4_face_exit     24
+
+enum {
+    atom_offset_cull_cube_g4_face_exit = _atom_offset_cull_cube_g4_face_exit,
+    atom_offset_bounds_chk_cube_g4_face_exit = _atom_offset_bounds_chk_cube_g4_face_exit,
+};
+
+// --- atom: floor_f3_face (58 words) ---
+
+#define _atom_offset_culling_floor_f3_face_exit       25
+#define _atom_offset_bounds_chk_floor_f3_face_exit    16
+
+enum {
+    atom_offset_culling_floor_f3_face_exit = _atom_offset_culling_floor_f3_face_exit,
+    atom_offset_bounds_chk_floor_f3_face_exit = _atom_offset_bounds_chk_floor_f3_face_exit,
+};
+
+#pragma endregion hello_gte.tape
+

code/hello_gte/hello_gte.c

@@ -20,10 +20,10 @@
 #include "duffle/lottes_tape.h"
 #include "duffle/word_count.metadata.h"
 
-#	include "gen/gte_hello.offsets.h"
+#	include "gen/hello_gte.offsets.h"
 #include "hello_gte.h"
 
-#include "hello_gte_tape.c"
+#include "hello_gte.tape.c"
 
 typedef U4 OrderingTable_Buffer[OrderingTbl_Len];
 typedef Array_(OrderingTable_Buffer, 2);

code/hello_gte/hello_gte.tape.c

@@ -4,7 +4,7 @@
 #	include "duffle/atom_dsl.h"
 #	include "duffle/lottes_tape.h"
 #	include "duffle/word_count.metadata.h"
-#	include "gen/gte_hello.offsets.h"
+#	include "gen/hello_gte.offsets.h"
 #	include "hello_gte.h"
 #endif
 
@@ -47,35 +47,34 @@ MipsAtom_(cube_g4_face) atom_info(atom_phase(cube_g4),
 	load_half_u(R_T3, R_FaceCursor, 3 * S_(S2)),
 
 	mac_gte_load_tri_verts(R_T0, R_T1, R_T2),
-	nop2, gte_cmdw_rotate_translate_perspective_triple,
+	nop2, gte_cmdw_rotate_translate_perspective_triple, // required cpu -> gte delay slot
-	nop2, gte_cmdw_nclip,
+	gte_cmdw_nclip,
 
-	nop2,  gte_mv_from_data_r(R_T0, C2_MAC0),
+	gte_mv_from_data_r(R_T0, C2_MAC0), nop,
-	nop,
 	branch_le_zero(R_T0, atom_offset(cull, cube_g4_face_exit)), nop,
-
 		store_word(R_0, R_PrimCursor, O_(Poly_G4, tag)),
+		shift_lleft(R_AT, R_T3, v3s2_byteoff), add_u(R_AT, R_AT, R_VertBase),
+		load_word(R_V0, R_AT, O_(V3_S2, x)),   load_word(R_V1, R_AT, O_(V3_S2, z)),
+		gte_mv_to_data_r(R_V0, C2_VXY0),       gte_mv_to_data_r(R_V1, C2_VZ0),
+
+		mac_gte_store_g4_p012(),
+		gte_cmdw_rotate_translate_perspective_single,
+		mac_gte_store_g4_p3(),
+
+		gte_cmdw_avg_sort_z4,
+		gte_mv_from_data_r(R_T1, C2_OTZ),
+		add_ui(      R_AT, R_0,  OrderingTbl_Len),
+		set_lt_u(    R_AT, R_T1, R_AT),
+
+		branch_equal(R_AT, R_0,  atom_offset(bounds_chk, cube_g4_face_exit)), nop,
+			mac_insert_ot_tag_g4(),
 			mac_format_g4_color(
 				/* c0 magenta */ 0xFF, 0x00, 0xFF,
 				/* c1 yellow  */ 0xFF, 0xFF, 0x00,
 				/* c2 cyan    */ 0x00, 0xFF, 0xFF,
 				/* c3 green   */ 0x00, 0xFF, 0x00),
-	mac_gte_store_g4_p012_post_rtpt_pre_rtps(),
+		// end: branch(bounds_chk)
-
+// end: branch(cull)
-	shift_lleft(R_AT, R_T3, v3s2_byteoff), add_u(R_AT, R_AT, R_VertBase),
-	load_word(R_V0, R_AT, O_(V3_S2, x)),   load_word(R_V1, R_AT, O_(V3_S2, z)),
-	gte_mv_to_data_r(R_V0, C2_VXY0),       gte_mv_to_data_r(R_V1, C2_VZ0),
-
-	nop2, gte_cmdw_rotate_translate_perspective_single,
-	mac_gte_store_g4_p3_post_rtps(),
-
-	nop2, gte_cmdw_avg_sort_z4,
-	nop2, gte_mv_from_data_r(R_T1, C2_OTZ),
-
-	add_ui(      R_AT, R_0,  OrderingTbl_Len),
-	set_lt_u(    R_AT, R_T1, R_AT),
-	branch_equal(R_AT, R_0,  atom_offset(bounds_chk, cube_g4_face_exit)), nop,
-	mac_insert_ot_tag_g4(),
 
 atom_label(cube_g4_face_exit)
 	add_ui_self(R_PrimCursor, S_(Poly_G4)),     /* 9 words = Poly_G4 */
@@ -103,11 +102,11 @@ MipsAtom_(rbind_floor_f3_face) atom_info(atom_bind(Binds_FloorTri), atom_phase(f
 	mac_yield()
 };
 
-atom_dbg_skip
+// atom_dbg_skip
 internal
 MipsAtom_(floor_f3_face) atom_info(atom_phase(floor_f3)
 	, atom_reads( R_PrimCursor, R_FaceCursor, R_VertBase, R_OtBase)
-	, atom_writes(R_PrimCursor, R_FaceCursr)
+	, atom_writes(R_PrimCursor, R_FaceCursor)
 ) {
 	mac_load_tri_indices(  R_T0, R_T1, R_T2),
 	mac_gte_load_tri_verts(R_T0, R_T1, R_T2),
@@ -118,8 +117,7 @@ MipsAtom_(floor_f3_face) atom_info(atom_phase(floor_f3)
 	gte_mv_from_data_r(R_T0, C2_MAC0),
 	nop, branch_le_zero(R_T0, atom_offset(culling, floor_f3_face_exit)), nop, // required gte -> cpu load-delay slot. 
 	/* Format Primitive */
-	mac_format_f3_color(0xFF, 0xFF, 0xFF),  // RGB-form (R=FF, G=FF, B=FF = white)
+	mac_gte_store_f3(),
-	mac_gte_store_f3_post_rtpt(),
 
 	/* Calculate Depth */
 	gte_avg_sort_z3,
@@ -128,8 +126,8 @@ MipsAtom_(floor_f3_face) atom_info(atom_phase(floor_f3)
 	add_ui(      R_AT, R_0,  OrderingTbl_Len),
 	set_lt_u(    R_AT, R_T1, R_AT),
 	branch_equal(R_AT, R_0,  atom_offset(bounds_chk, floor_f3_face_exit)), nop,
-	/* Insert into Ordering Table Linked List */
+	mac_format_f3_color(0xFF, 0xFF, 0xFF),  // RGB-form (R=FF, G=FF, B=FF = white)
-	mac_insert_ot_tag_f3(),
+	mac_insert_ot_tag_f3(),                 /* Insert into Ordering Table Linked List */
 	add_ui_self(R_PrimCursor, S_(Poly_F3)), /* Advance Prim Cursor (5 words) */
 		// Note(Ed): No bounds checking, should be checked before atom runs.
 

code/hello_joypad/gen/hello_joypad.offsets.h

@@ -0,0 +1,29 @@
+// Auto-generated by ps1_meta.lua (passes/offsets.lua) — DO NOT EDIT
+// Source: C:\projects\Pikuma\ps1\code\hello_joypad\hello_joypad.tape.c
+#pragma once
+
+#pragma region hello_joypad.tape
+
+
+// --- atom: cube_g4_face (77 words) ---
+
+#define _atom_offset_cull_cube_g4_face_exit           42
+#define _atom_offset_bounds_chk_cube_g4_face_exit     24
+
+enum {
+    atom_offset_cull_cube_g4_face_exit = _atom_offset_cull_cube_g4_face_exit,
+    atom_offset_bounds_chk_cube_g4_face_exit = _atom_offset_bounds_chk_cube_g4_face_exit,
+};
+
+// --- atom: floor_f3_face (58 words) ---
+
+#define _atom_offset_culling_floor_f3_face_exit       25
+#define _atom_offset_bounds_chk_floor_f3_face_exit    16
+
+enum {
+    atom_offset_culling_floor_f3_face_exit = _atom_offset_culling_floor_f3_face_exit,
+    atom_offset_bounds_chk_floor_f3_face_exit = _atom_offset_bounds_chk_floor_f3_face_exit,
+};
+
+#pragma endregion hello_joypad.tape
+

code/hello_joypad/hello_joypad.c

@@ -0,0 +1,430 @@
+#include <stdio.h>
+#include <stdlib.h>
+#include <assert.h>
+// #include "libgpu.h"
+// #include "libetc.h"
+// #include "libgte.h"
+
+#include "duffle/dsl.h"
+#include "duffle/memory.h"
+#include "duffle/math.h"
+
+#include "duffle/gcc_asm.h"
+#include "duffle/mips.h"
+#include "duffle/gp.h"
+#include "duffle/gte.h"
+
+#	include "duffle/gen/duffle.macs.h"
+#	include "duffle/gen/duffle.offsets.h"
+#include "duffle/atom_dsl.h"
+#include "duffle/lottes_tape.h"
+#include "duffle/word_count.metadata.h"
+
+#	include "gen/hello_joypad.offsets.h"
+#include "hello_joypad.h"
+
+#include "hello_joypad.tape.c"
+
+typedef U4 OrderingTable_Buffer[OrderingTbl_Len];
+typedef Array_(OrderingTable_Buffer, 2);
+
+typedef B1 PrimitiveBuffer[PrimitiveBuff_Len];
+typedef Array_(PrimitiveBuffer, 2);
+typedef Struct_(PrimitiveArena) {
+	A2_PrimitiveBuffer buf;
+	U4                 used;
+};
+
+#define Cube_num_verts 8
+typedef Array_(V3_S2, Cube_num_verts);
+#define Cube_num_faces 6
+typedef Array_(V4_S2, Cube_num_faces);
+I_ void ent_cube128_init(A8_V3_S2* verts, A6_V4_S2* faces) {
+	LP_ A8_V3_S2 baked_verts = (A8_V3_S2) {
+		{ -128, -128, -128 },
+		{  128, -128, -128 },
+		{  128, -128,  128 },
+		{ -128, -128,  128 },
+		{ -128,  128, -128 },
+		{  128,  128, -128 },
+		{  128,  128,  128 },
+		{ -128,  128,  128 }
+	};
+	LP_ A6_V4_S2 baked_faces = (A6_V4_S2) {
+		{ 3, 2, 0, 1 },
+		{ 0, 1, 4, 5 },
+		{ 4, 5, 7, 6 },
+		{ 1, 2, 5, 6 },
+		{ 2, 3, 6, 7 },
+		{ 3, 0, 7, 4 },
+	};
+	mem_copy(u4_(verts), u4_(& baked_verts), S_(A8_V3_S2) );
+	mem_copy(u4_(faces), u4_(& baked_faces), S_(A6_V4_S2) );
+	return;
+}
+typedef Struct_(Ent_Cube) {
+	V3_S4 accel;
+	V3_S4 vel;
+	V3_S4 pos;
+	V3_S4 scale;
+	V3_S2 rot;
+	A8_V3_S2 verts;
+	A6_V4_S2 faces;
+};
+
+#define Floor_num_verts 4
+typedef Array_(V3_S2, Floor_num_verts);
+#define Floor_num_faces 2
+typedef Array_(V3_S2, Floor_num_faces);
+I_ void ent_floor_init(A4_V3_S2* verts, A2_V3_S2* faces) {
+	LP_ A4_V3_S2 baked_verts = (A4_V3_S2) {
+		{ -900, 0, -900 },
+		{ -900, 0,  900 },
+		{  900, 0, -900 },
+		{  900, 0,  900 },
+	};
+	LP_ A2_V3_S2 baked_faces = (A2_V3_S2) {
+		{ 0, 1, 2 },
+		{ 1, 3, 2 },
+	};
+	mem_copy(u4_(verts), u4_(& baked_verts), S_(A4_V3_S2));
+	mem_copy(u4_(faces), u4_(& baked_faces), S_(A2_V3_S2));
+};
+typedef Struct_(Ent_Floor) {
+	V3_S4 accel;
+	V3_S4 pos;
+	V3_S4 scale;
+	V3_S2 rot;
+	A4_V3_S2 verts;
+	A2_V3_S2 faces;
+};
+
+enum { 
+	Scratchpad_Len = 1024, 
+	MemTape_Len    = 512,
+};
+typedef Struct_(SMemory) {
+	U4 MemTape[MemTape_Len];
+
+	DoubleBuffer            screen_buf;
+	A2_OrderingTable_Buffer ordering_tbl;
+	PrimitiveArena          primitives;
+	S4                      active_buf_id;
+
+	M3_S2 tform_world;
+
+	Ent_Cube  cube;
+	Ent_Floor floor;
+
+	U4_V scratchpad; // d-cache
+};
+global SMemory smem;
+extern SMemory smem;
+
+// TODO(Ed):
+FI_ U4* spad_warm(MipsAtom atom) {
+	return nullptr;
+}
+
+I_ B1* prim__alloc(U4 type_width, Str8 type_name) {
+	gknown PrimitiveArena* pa  = & smem.primitives;
+	gknown B1*             buf = (B1*) r_(smem.primitives.buf)[smem.active_buf_id];
+	assert(pa->used + type_width < PrimitiveBuff_Len);
+	B1* next  = buf + pa->used;
+	pa->used += type_width;
+	return next;
+}
+#define prim_alloc(type) (type*)prim__alloc(S_(type), slit( stringify(type)))
+
+void gp_screen_init_c11(DoubleBuffer* screen_buf, S4* active_buf_id)
+{
+	reset_graph(0);
+
+	// Set the current initial buffer
+	active_buf_id[0] = 0;
+
+	// Just setting env data, not interacting with console hw.
+	// First buffer area
+	displayenv_init(& r_(screen_buf->display)[0], 0, 0,           ScreenRes_X, ScreenRes_Y);
+	drawenv_init   (& r_(screen_buf->draw   )[0], 0, ScreenRes_Y, ScreenRes_X, ScreenRes_Y);
+	// Second buffer area
+	displayenv_init(& r_(screen_buf->display)[1], 0, ScreenRes_Y, ScreenRes_X, ScreenRes_Y);
+	drawenv_init   (& r_(screen_buf->draw   )[1], 0, 0,           ScreenRes_X, ScreenRes_Y);
+	// Set the back/drawing buffer
+	screen_buf->draw[0].enable_auto_clear = true;
+	screen_buf->draw[1].enable_auto_clear = true;
+	// Set the background clear color
+	screen_buf->draw[0].initial_bg_color = rgb8( .r = 7, .g = 7,  .b = 7 );
+	screen_buf->draw[1].initial_bg_color = rgb8( .r = 7, .g = 7,  .b = 7 );
+	// screen_buf->draw[1].initial_bg_color = rgb8( .r = 47, .g = 13, .b = 0 );
+	displayenv_put(& r_(screen_buf->display)[ active_buf_id[0] ]);
+	drawenv_put   (& r_(screen_buf->draw   )[ active_buf_id[0] ]);
+
+	// Initialize and setup the GTE geometry offsets
+	geom_init();
+	// NOTE: geom_set_offset/geom_set_screen are kept as-is (the libgte versions
+	// are known to be broken in this PSYQ 4.7 build — see report 2026-07-09).
+	// The user's research wants the C-side non-tape reference to work as a
+	// known-good baseline for comparison against the tape.
+	geom_set_offset(ScreenRes_CenterX, ScreenRes_CenterY);
+	geom_set_screen(ScreenZ);
+
+	set_display_enabled(1); // gp_DisplayEnabled
+}
+
+void gp_display_frame(DoubleBuffer* screen_buf, S4* active_buf_id, U4* ordering_buf, PrimitiveArena* pa) {
+	draw_sync(0);
+	vsync(0);
+	displayenv_put(& r_(screen_buf->display)[active_buf_id[0] ]);
+	drawenv_put   (& r_(screen_buf->draw)   [active_buf_id[0] ]);
+	{
+		draw_orderingtbl(ordering_buf + OrderingTbl_Len - 1);
+		pa->used = 0;
+	}
+	active_buf_id[0] = ! active_buf_id[0]; // Swap current buffer
+}
+
+void render(void) {
+}
+
+GCC_OPTIMIZATION_DISABLE
+void update(PrimitiveArena* pa, U4* ordering_buf) 
+{
+	orderingtbl_clear_reverse(ordering_buf, OrderingTbl_Len);
+
+	// Update the position based on acceleration and velocity
+	gknown V3_S4_R pos = & smem.cube.pos;
+	gknown V3_S4_R vel = & smem.cube.vel;
+	gknown V3_S4_R acc = & smem.cube.accel;
+	add_v3s4(vel, acc[0]);
+	add_v3s4_fp(pos, vel[0]);
+	// vel->x += acc->x;
+	// vel->y += acc->y;
+	// vel->z += acc->z;
+	// pos->x += vel->x;
+	// pos->y += vel->y;
+	// pos->z += vel->z;
+
+	if (pos->y + 150 > smem.floor.pos.y) vel->y *= -1;
+
+	// Prep
+	S4 nclip = 0;
+	S4 orderingtbl_z = 0;
+	A2_S2 p;    //???
+	S4 flag; //????
+
+	TapeBuilder tb = tb_make(slice_ut_arr(smem.MemTape));
+
+	// Draw Cube
+	if (0)
+	{
+		m3s2_rotation   (& smem.cube.rot,    & smem.tform_world);
+		m3s2_translation(& smem.tform_world, & smem.cube.pos);
+		m3s2_scale      (& smem.tform_world, & smem.cube.scale);
+		// gte_matrix_set_rotation   (& smem.tform_world);
+		gte_matrix_set_translation(& smem.tform_world);
+		for (U4 face_id = 0; face_id < Cube_num_faces; face_id += 1)
+		{
+			Poly_G4* quad = prim_alloc(Poly_G4); set_poly_g4(quad);
+			quad->c0 = rgb8(255,   0, 255);
+			quad->c1 = rgb8(255, 255,   0);
+			quad->c2 = rgb8(  0, 255, 255);
+			quad->c3 = rgb8(  0, 255,   0);
+
+			V4_S2* face = & smem.cube.faces[face_id];
+			V3_S2* p0   = & smem.cube.verts[face->x];
+			V3_S2* p1   = & smem.cube.verts[face->y];
+			V3_S2* p2   = & smem.cube.verts[face->z];
+			V3_S2* p3   = & smem.cube.verts[face->w];
+
+			nclip = rtp_avg_nclip_a4_v3s2(
+				p0, p1, p2, p3,
+				& quad->p0, & quad->p1, & quad->p2, & quad->p3,
+				& p, & orderingtbl_z, & flag
+			);
+			if (nclip <= 0) {
+				continue;
+			}
+
+			if ((orderingtbl_z > 0) && (orderingtbl_z < OrderingTbl_Len)) {
+				orderingtbl_add_primitive(ordering_buf[orderingtbl_z], quad);
+			}
+		}
+		// smem.cube.rot.x +=  6;
+		// smem.cube.rot.y +=  8;
+		// smem.cube.rot.z += 12;
+		smem.cube.rot.y += 30;
+	}
+	// Draw cube (tape method) - two triangles per face
+	if (1)
+	{
+		m3s2_rotation   (& smem.cube.rot,    & smem.tform_world);
+		m3s2_translation(& smem.tform_world, & smem.cube.pos);
+		m3s2_scale      (& smem.tform_world, & smem.cube.scale);
+		gte_matrix_set_rotation   (& smem.tform_world);
+		gte_matrix_set_translation(& smem.tform_world);
+
+		U4 prim_base   = u4_(pa->buf[smem.active_buf_id]);
+		U4 prim_cursor = prim_base + pa->used;
+
+		tb.used = 0; tb_scope(& tb) {
+			tb_emit(& tb, rbind_cube_g4_face);
+				tb_data(& tb, prim_cursor);
+				tb_data(& tb, u4_(smem.cube.faces));
+				tb_data(& tb, u4_(smem.cube.verts));
+				tb_data(& tb, u4_(ordering_buf));
+
+			for (U4 i = 0; i < Cube_num_faces; i++) {
+				// Two triangles per quad face: (x,y,z) and (x,z,w)
+				tb_emit(& tb, cube_g4_face);
+			}
+
+			tb_emit(& tb, sync_primitive_arena);
+				tb_data(& tb, u4_(& pa->used));
+				tb_data(& tb, prim_base);
+		}
+		tape_run(tb_slice(tb));
+
+		smem.cube.rot.y += 30;
+	}
+	// Draw Floor
+	if (0)
+	{
+		m3s2_rotation   (& smem.floor.rot,   & smem.tform_world);
+		m3s2_translation(& smem.tform_world, & smem.floor.pos);
+		m3s2_scale      (& smem.tform_world, & smem.floor.scale);
+		gte_matrix_set_rotation   (& smem.tform_world);
+		gte_matrix_set_translation(& smem.tform_world);
+		for (U4 face_id = 0; face_id < Floor_num_faces; face_id += 1)
+		{
+			Poly_F3* tri = prim_alloc(Poly_F3); set_poly_f3(tri);
+			tri->color   = rgb8(255, 255, 255);
+
+			V3_S2* face = & smem.floor.faces[face_id];
+			register V3_S2* p0 rgcc(R_T4) = & smem.floor.verts[face->x];
+			register V3_S2* p1 rgcc(R_T5) = & smem.floor.verts[face->y];
+			register V3_S2* p2 rgcc(R_T6) = & smem.floor.verts[face->z];
+
+			gte_load_v0(p0, R_T4);
+			/*
+			asm volatile( ".word " "%0" ", %1" : : 
+				"i"(((op_lwc2 & OPCODE_MASK) << OPCODE_SHIFT) | ((R_T4 & REG_MASK) << RS_SHIFT) | ((gte_in_v0_xy & REG_MASK) << RT_SHIFT) | (0            & IMM_MASK)),
+				"i"(((op_lwc2 & OPCODE_MASK) << OPCODE_SHIFT) | ((R_T4 & REG_MASK) << RS_SHIFT) | ((gte_in_v0_z  & REG_MASK) << RT_SHIFT) | (GTE_Z_Offset & IMM_MASK)), 
+				"r"(p0) : 
+				"$2", "$8", "$9", "$31", "memory" 
+			);
+			*/
+			gte_load_v1(p1, R_T5);
+			gte_load_v2(p2, R_T6);
+
+			gte_rtpt();
+			gte_nclip();
+			gte_stotz(& nclip);
+
+			// nclip = rtp_avg_nclip_a3_v3s2(p0, p1, p2
+			// 	, & tri->p0, & tri->p1, & tri->p2
+			// 	, & p, & orderingtbl_z, & flag
+			// );
+			// if (nclip <= 0) {
+			// 	continue;
+			// }
+
+			if (nclip > 0 ) {
+				gte_stsxy3(& tri->p0, & tri->p1, & tri->p2);
+				gte_avsz3();
+				gte_stotz(& orderingtbl_z);
+
+				if ((orderingtbl_z > 0) && (orderingtbl_z < OrderingTbl_Len)) {
+					orderingtbl_add_primitive(ordering_buf[orderingtbl_z], tri);
+				}
+			}
+		}
+		smem.floor.rot.y += 5;
+	}
+	// Draw floor tape method
+	if (1)
+	{
+		m3s2_rotation   (& smem.floor.rot,   & smem.tform_world);
+		m3s2_translation(& smem.tform_world, & smem.floor.pos);
+		m3s2_scale      (& smem.tform_world, & smem.floor.scale);
+
+		U4 prim_base   = u4_(pa->buf[smem.active_buf_id]);
+		U4 prim_cursor = prim_base + pa->used;
+
+		// TODO(Ed): We should do a bounds check beforehand to confirm pa can hold all tris?
+		// The tape atoms in-flight should not need to care.
+
+		// Prepare the tape. (Push protocol to tape)
+		tb.used = 0; tb_scope(& tb) {
+			tb_emit(& tb, set_gte_world);
+				tb_data(& tb, u4_(& smem.tform_world));
+
+			tb_emit(& tb, rbind_floor_f3_face);
+			// TODO(Ed): Just use a single context struct ref
+				tb_data(& tb, prim_cursor);
+				tb_data(& tb, u4_(smem.floor.faces));
+				tb_data(& tb, u4_(smem.floor.verts));
+				tb_data(& tb, u4_(ordering_buf));
+			for (U4 i = 0; i < Floor_num_faces; i++) {
+				tb_emit(& tb, floor_f3_face);
+			}
+			// After floor_f3_face iterations complete, the primitive arena's used counter needs updating.
+			tb_emit(& tb, sync_primitive_arena);
+				tb_data(& tb, u4_(& pa->used));
+				tb_data(& tb, prim_base);
+		}
+		tape_run(tb_slice(tb));// Fire off the tape.
+
+		// C-side state (pa->used) has already been updated by the tape!
+		smem.floor.rot.y += 5;
+	}
+	// --- TAPE DIAGNOSTICS ---
+	if (0)
+	{
+		LP_ U4 mem_temp_tape[512]; FArena tape_arena; farena_init(& tape_arena, slice_ut_arr(mem_temp_tape));
+		TapeBuilder tb = tb_make_old(& tape_arena); tb_scope(& tb) {
+			// Skip set_gte_world atom for diagnostics to isolate the triangle loop
+			for (U4 i = 0; i < Floor_num_faces; i++) {
+				// tb_emit(& tb, code_diag_yield);
+				// tb_emit(& tb, code_diag_color);
+				// tb_emit(& tb, code_diag_gte); 
+			}
+		}
+		B1* prim_cursor = (B1*)r_(pa->buf)[smem.active_buf_id] + pa->used;
+		tape_run(tb_slice(tb));
+		pa->used = (U4)prim_cursor - (U4)r_(pa->buf)[smem.active_buf_id];
+	}
+}
+GCC_OPTIMIZATION_ENABLE
+
+int main(void)
+{
+	smem = (SMemory){0};
+	smem.scratchpad = C_(U4_V, 0x1F800000);
+	smem.primitives.used = 0;
+	ent_cube128_init(& smem.cube.verts, & smem.cube.faces); {
+		Ent_Cube* cube = & smem.cube;
+		cube->rot    = v3s2(0, 0, 0);
+		// cube->pos    = v3s4(0, 0, 900);
+		cube->scale  = v3s4_fp_one();
+		cube->accel  = v3s4(0, 1, 0);
+		cube->pos    = v3s4(0, -400, 1800);
+	}
+	ent_floor_init(& smem.floor.verts, & smem.floor.faces); {
+		Ent_Floor* floor = & smem.floor;
+		floor->rot   = v3s2(0, 0, 0);
+		floor->pos   = v3s4(0, 450, 1800);
+		floor->scale = v3s4_fp_one();
+	}
+	// gknown gp_screen_init();
+	gp_screen_init_c11(& smem.screen_buf, & smem.active_buf_id);
+	while (1) {
+		gknown S4* active_buf_id  = & smem.active_buf_id;
+		gknown U4* ordering_buf   = r_(smem.ordering_tbl)[active_buf_id[0]];
+		gknown PrimitiveArena* pa = & smem.primitives;
+		update(pa, ordering_buf);
+		render();
+		gp_display_frame(& smem.screen_buf, active_buf_id, ordering_buf, pa);
+	};
+	return 0;
+}

code/hello_joypad/hello_joypad.h

@@ -0,0 +1,119 @@
+#ifdef INTELLISENSE_DIRECTIVES
+#	pragma once
+#	include "duffle/dsl.h"
+#	include "duffle/math.h"
+#	include "duffle/gp.h"
+#endif
+
+enum {
+	PrimitiveBuff_Len = 4096,
+	OrderingTbl_Len   = 2048
+};
+
+typedef Struct_(DrawEnv_Packed) { U4 tag; U4 code[15]; };
+typedef Struct_(DrawEnv) {
+	Rect_S2 clip_area;
+	A2_S2   drawing_offset;
+	Rect_S2 texture_window;
+	S2      texture_page;
+	B1      flag_dither;	
+	B1      flag_draw_on_display;
+	B1      enable_auto_clear;
+	RGB8    initial_bg_color;
+	DrawEnv_Packed dr_env; // reserved
+};
+typedef Struct_(DisplayEnv) {
+	Rect_S2 display_area;
+	Rect_S2 screen;
+	B1      vinterlace;
+	B1      color24;
+	B1      pad0;
+	B1      pad1;
+};
+typedef Array_(DrawEnv,    2);
+typedef Array_(DisplayEnv, 2);
+typedef Struct_(DoubleBuffer) {
+	A2_DrawEnv    draw;
+	A2_DisplayEnv display;
+};
+
+#define ScreenRes_X 320
+#define ScreenRes_Y 240
+#define ScreenZ     320
+#define ScreenRes_CenterX (ScreenRes_X >> 1)
+#define ScreenRes_CenterY (ScreenRes_Y >> 1)
+
+DisplayEnv* displayenv_init(DisplayEnv* env, S4 x, S4 y, S4 w, S4 h) __asm__("SetDefDispEnv");
+DrawEnv*    drawenv_init   (DrawEnv*    env, S4 x, S4 y, S4 w, S4 h) __asm__("SetDefDrawEnv");
+
+DisplayEnv* displayenv_put(DisplayEnv* env) __asm__("PutDispEnv");
+DrawEnv*    drawenv_put   (DrawEnv*    env) __asm__("PutDrawEnv");
+
+U4   geom_init(void)             __asm__("InitGeom");
+void geom_set_offset(U4 x, U4 y) __asm__("SetGeomOffset");
+void geom_set_screen(U4 h)       __asm__("SetGeomScreen");
+
+U4* orderingtbl_clear_reverse(U4* ot, U4 len) __asm__("ClearOTagR");
+
+U4 reset_graph(U4 mode)           __asm__("ResetGraph");
+void set_display_enabled(U4 mask) __asm__("SetDispMask");
+
+U4 draw_sync(U4 mode) __asm__("DrawSync");
+U4 vsync(U4 mode)     __asm__("VSync");
+
+void draw_orderingtbl(U4* buf) __asm__("DrawOTag");
+
+typedef Struct_(Tile) {
+	U4      tag;
+	RGB8    color;
+	B1      code;
+	Rect_S2 rect;
+};
+
+/*
+	Linear Algebra
+*/
+
+M3_S2* m3s2_rotation   (V3_S2* vec, M3_S2* mat) __asm__("RotMatrix");
+M3_S2* m3s2_translation(M3_S2* mat, V3_S4* vec) __asm__("TransMatrix");
+M3_S2* m3s2_scale      (M3_S2* mat, V3_S4* vec) __asm__("ScaleMatrix");
+
+// Rotation, Translation, Perspective
+
+S4 rtp_v3s2_raw(V3_S2* vec, S4* xy, S4* pp, S4* flag) __asm__("RotTransPers");
+FI_ S4 rtp_v3s2(V3_S2* vec, V2_S2* xy, A2_S2* pp, S4* flag) { return rtp_v3s2_raw(vec, C_(S4*R_, & xy->x), C_(S4*R_, pp), r_(flag)); }
+
+S4 rtp_avg_nclip_a3_v3s2_raw(V3_S2* v0, V3_S2* v1, V3_S2* v2, S4* xy1, S4* xy2, S4* xy3, S4* pp, S4* otz, S4* flag) __asm__("RotAverageNclip3");
+FI_  S4 rtp_avg_nclip_a3_v3s2(
+	V3_S2* v0,  V3_S2* v1,  V3_S2* v2, 
+	V2_S2* xy0, V2_S2* xy1, V2_S2* xy2, 
+	A2_S2* pp, S4* otz, S4* flag
+){
+	return rtp_avg_nclip_a3_v3s2_raw(
+		v0, v1, v2, 
+		C_(S4*R_, xy0), C_(S4*R_, xy1), C_(S4*R_, xy2),
+		C_(S4*R_, pp),  C_(S4*R_, otz), C_(S4*R_, flag)
+	);
+}
+
+S4 rtp_avg_nclip_a4_v3s2_raw(V3_S2* v0, V3_S2* v1, V3_S2* v2, V3_S2* v3, S4* xy1, S4* xy2, S4* xy3, S4* xy4, S4* pp, S4* otz, S4* flag) __asm__("RotAverageNclip4");
+FI_ S4 rtp_avg_nclip_a4_v3s2(
+	V3_S2* v0,  V3_S2* v1,  V3_S2* v2,  V3_S2* v3,
+	V2_S2* xy0, V2_S2* xy1, V2_S2* xy2, V2_S2* xy3,
+	A2_S2* pp,  S4* otz,    S4* flag
+){
+	return rtp_avg_nclip_a4_v3s2_raw(
+		v0, v1, v2, v3,
+		C_(S4*R_, xy0), C_(S4*R_, xy1), C_(S4*R_, xy2), C_(S4*R_, xy3),
+		C_(S4*R_, pp),  C_(S4*R_, otz), C_(S4*R_, flag)
+	);
+}
+
+void gte_matrix_set_rotation   (M3_S2* mat) __asm__("SetRotMatrix");
+void gte_matrix_set_translation(M3_S2* mat) __asm__("SetTransMatrix");
+
+enum {
+	fp_one = (1 << 12),
+};
+
+#define v3s4_fp_one() v3s4(fp_one, fp_one, fp_one)

code/hello_joypad/hello_joypad.tape.c

@@ -0,0 +1,154 @@
+#ifdef INTELLISENSE_DIRECTIVES
+#	include "duffle/gen/duffle.macs.h"
+#	include "duffle/gen/duffle.offsets.h"
+#	include "duffle/atom_dsl.h"
+#	include "duffle/lottes_tape.h"
+#	include "duffle/word_count.metadata.h"
+#	include "gen/hello_joypad.offsets.h"
+#	include "hello_joypad.h"
+#endif
+
+#pragma region MACs (Mips Atom components)
+
+
+
+#pragma endregion MACs
+
+#pragma region Baked Atoms
+
+typedef Struct_(Binds_CubeTri) {
+	U4     PrimCursor;
+	V4_S2* FaceCursor;
+	V3_S2* VertBase;
+	U4*    OtBase;
+};
+internal MipsAtom_(rbind_cube_g4_face) atom_info(atom_bind(Binds_CubeTri), atom_phase(cube_g4)
+,	atom_reads(R_TapePtr)
+,	atom_writes(R_PrimCursor, R_FaceCursor, R_VertBase, R_OtBase)
+){
+	/* Pop 4 arguments from the tape directly into the workspace registers */
+	load_word(R_PrimCursor, R_TapePtr, O_(Binds_CubeTri,PrimCursor)),
+	load_word(R_FaceCursor, R_TapePtr, O_(Binds_CubeTri,FaceCursor)),
+	load_word(R_VertBase,   R_TapePtr, O_(Binds_CubeTri,VertBase)),
+	load_word(R_OtBase,     R_TapePtr, O_(Binds_CubeTri,OtBase)),
+	add_ui_self(            R_TapePtr, S_(Binds_CubeTri)),
+	mac_yield()
+};
+
+ // cube_g4_face — Draw one cube face (Gouraud-shaded quad) via the GTE tape pipeline
+internal
+MipsAtom_(cube_g4_face) atom_info(atom_phase(cube_g4),
+		atom_reads( R_PrimCursor, R_FaceCursor, R_VertBase, R_OtBase),
+		atom_writes(R_PrimCursor, R_FaceCursor)
+){
+	load_half_u(R_T0, R_FaceCursor, 0 * S_(S2)),
+	load_half_u(R_T1, R_FaceCursor, 1 * S_(S2)),
+	load_half_u(R_T2, R_FaceCursor, 2 * S_(S2)),
+	load_half_u(R_T3, R_FaceCursor, 3 * S_(S2)),
+
+	mac_gte_load_tri_verts(R_T0, R_T1, R_T2),
+	nop2, gte_cmdw_rotate_translate_perspective_triple, // required cpu -> gte delay slot
+	gte_cmdw_nclip,
+
+	gte_mv_from_data_r(R_T0, C2_MAC0), nop,
+	branch_le_zero(R_T0, atom_offset(cull, cube_g4_face_exit)), nop,
+		store_word(R_0, R_PrimCursor, O_(Poly_G4, tag)),
+		shift_lleft(R_AT, R_T3, v3s2_byteoff), add_u(R_AT, R_AT, R_VertBase),
+		load_word(R_V0, R_AT, O_(V3_S2, x)),   load_word(R_V1, R_AT, O_(V3_S2, z)),
+		gte_mv_to_data_r(R_V0, C2_VXY0),       gte_mv_to_data_r(R_V1, C2_VZ0),
+
+		mac_gte_store_g4_p012(),
+		gte_cmdw_rotate_translate_perspective_single,
+		mac_gte_store_g4_p3(),
+
+		gte_cmdw_avg_sort_z4,
+		gte_mv_from_data_r(R_T1, C2_OTZ),
+		add_ui(      R_AT, R_0,  OrderingTbl_Len),
+		set_lt_u(    R_AT, R_T1, R_AT),
+
+		branch_equal(R_AT, R_0,  atom_offset(bounds_chk, cube_g4_face_exit)), nop,
+			mac_insert_ot_tag_g4(),
+			mac_format_g4_color(
+				/* c0 magenta */ 0xFF, 0x00, 0xFF,
+				/* c1 yellow  */ 0xFF, 0xFF, 0x00,
+				/* c2 cyan    */ 0x00, 0xFF, 0xFF,
+				/* c3 green   */ 0x00, 0xFF, 0x00),
+		// end: branch(bounds_chk)
+// end: branch(cull)
+
+atom_label(cube_g4_face_exit)
+	add_ui_self(R_PrimCursor, S_(Poly_G4)),     /* 9 words = Poly_G4 */
+	add_ui_self(R_FaceCursor, S_(S2) * 4),      /* 4 × S2 = 8 bytes */
+	mac_yield()
+};
+
+typedef Struct_(Binds_FloorTri) {
+	U4     PrimCursor;
+	V3_S2* FaceCursor;
+	V3_S2* VertBase;
+	U4*    OtBase;
+};
+internal
+MipsAtom_(rbind_floor_f3_face) atom_info(atom_bind(Binds_FloorTri), atom_phase(floor_f3)
+	, atom_reads(R_TapePtr)
+	, atom_writes(R_PrimCursor, R_FaceCursor, R_VertBase, R_OtBase)
+){
+	/* Pop 4 arguments from the tape directly into the workspace registers */
+	load_word(R_PrimCursor, R_TapePtr, O_(Binds_FloorTri,PrimCursor)),
+	load_word(R_FaceCursor, R_TapePtr, O_(Binds_FloorTri,FaceCursor)),
+	load_word(R_VertBase,   R_TapePtr, O_(Binds_FloorTri,VertBase)),
+	load_word(R_OtBase,     R_TapePtr, O_(Binds_FloorTri,OtBase)),
+	add_ui_self(            R_TapePtr, S_(Binds_FloorTri)),
+	mac_yield()
+};
+
+// atom_dbg_skip
+internal
+MipsAtom_(floor_f3_face) atom_info(atom_phase(floor_f3)
+	, atom_reads( R_PrimCursor, R_FaceCursor, R_VertBase, R_OtBase)
+	, atom_writes(R_PrimCursor, R_FaceCursor)
+) {
+	mac_load_tri_indices(  R_T0, R_T1, R_T2),
+	mac_gte_load_tri_verts(R_T0, R_T1, R_T2),
+	nop2, gte_cmdw_rotate_translate_perspective_triple, // 2 nops retire the final cpu -> gte writes before RTPT
+	gte_cmdw_nclip,
+
+	/* Culling (Branch forward if Backface) */
+	gte_mv_from_data_r(R_T0, C2_MAC0),
+	nop, branch_le_zero(R_T0, atom_offset(culling, floor_f3_face_exit)), nop, // required gte -> cpu load-delay slot. 
+	/* Format Primitive */
+	mac_gte_store_f3(),
+
+	/* Calculate Depth */
+	gte_avg_sort_z3,
+	gte_mv_from_data_r(R_T1, C2_OTZ),
+	/* Bounds Check OTZ < 2048 (Branch forward to skip insertion) */
+	add_ui(      R_AT, R_0,  OrderingTbl_Len),
+	set_lt_u(    R_AT, R_T1, R_AT),
+	branch_equal(R_AT, R_0,  atom_offset(bounds_chk, floor_f3_face_exit)), nop,
+	mac_format_f3_color(0xFF, 0xFF, 0xFF),  // RGB-form (R=FF, G=FF, B=FF = white)
+	mac_insert_ot_tag_f3(),                 /* Insert into Ordering Table Linked List */
+	add_ui_self(R_PrimCursor, S_(Poly_F3)), /* Advance Prim Cursor (5 words) */
+		// Note(Ed): No bounds checking, should be checked before atom runs.
+
+/* Advance Input Cursor & Yield (Both branch targets land here) */
+atom_label(floor_f3_face_exit)
+	add_ui_self(R_FaceCursor, S_(S2) * 4),  /* Advance Face Cursor (4 * S2 = 8 bytes) */
+	mac_yield()
+};
+
+typedef Struct_(Binds_SyncPrimitiveArena) { U4 used; U4 cursor; };
+internal MipsAtom_(sync_primitive_arena) atom_info(atom_bind(Binds_SyncPrimitiveArena)
+	, atom_reads( R_TapePtr, R_PrimCursor)
+	, atom_writes(R_TapePtr)
+){
+	load_word(R_AT, R_TapePtr, O_(Binds_SyncPrimitiveArena,used)),
+	load_word(R_T0, R_TapePtr, O_(Binds_SyncPrimitiveArena,cursor)),
+	add_ui_self(    R_TapePtr, S_(Binds_SyncPrimitiveArena)),
+	/* Calculate byte offset and store directly back to RAM */
+	sub_u(     R_T0, R_PrimCursor, R_T0), // R_T0    = R_PrimCursor - binds.cursor
+	store_word(R_T0, R_AT, 0),            // R_AT[0] = R_T0
+	mac_yield()
+};
+
+#pragma endregion Baked Atoms

scripts/build_psyq.ps1

@@ -350,10 +350,10 @@ function build-graphis_hello {
 }
 # build-graphis_hello
 
-function build-gte_hello {
+function build-hello_gte {
 	$includes += @()
 
-	$path_module        = join-path $path_code   'gte_hello'
+	$path_module        = join-path $path_code   'hello_gte'
 	$path_duffle        = join-path $path_code   'duffle'
 	$path_atom_metadata = join-path $path_duffle 'word_count.metadata.h'
 	$path_build_gen     = join-path $path_build   'gen'
@@ -458,8 +458,112 @@ function build-gte_hello {
 		}
 	}
 }
-build-gte_hello
+# build-hello_gte
 
+function build-hello_joypad {
+	$includes += @()
+
+	$path_module        = join-path $path_code   'hello_joypad'
+	$path_duffle        = join-path $path_code   'duffle'
+	$path_atom_metadata = join-path $path_duffle 'word_count.metadata.h'
+	$path_build_gen     = join-path $path_build  'gen'
+
+	$src_c = join-path $path_module 'hello_joypad.c'
+	ps1-meta -unity_root $src_c -metadata $path_atom_metadata -out_root $path_build_gen
+
+	$assemble_args = @()
+	$assemble_args += $f_debug
+	$assemble_args += $f_optimize_none
+	$assemble_args += ($f_include + $path_code)
+
+	$src_asm_crt    = join-path $path_nugget_common 'crt0/crt0.s'
+	$module_asm_crt = join-path $path_build         'crt0.o'
+	assemble-unit $src_asm_crt $module_asm_crt $includes $assemble_args
+
+	$module_c = join-path $path_build  'hello_joypad_c.o'
+
+	$compile_args = @()
+	$compile_args += $f_debug
+	$compile_args += $f_optimize_none
+	# $compile_args += $f_optimize_intrinsics
+	# $compile_args += $f_optimize_size
+	# $compile_args += $f_optimize_debug
+	$compile_args += ($f_include + $path_code)
+	compile-unit $src_c $module_c $includes $compile_args
+
+	$elf = join-path $path_build 'hello_joypad.elf'
+	$exe = join-path $path_build 'hello_joypad.ps-exe'
+
+	$link_args = @()
+	$link_args += $f_debug
+	# $link_args += $f_optimize_size
+	$link_modules = @(
+		$module_asm_crt,
+		$module_c
+	)
+	link-modules $link_modules $elf $link_args
+	make-binary $elf $exe
+
+	# Post-link: gdb-runtime + dwarf-injection in a single Lua invocation (one luajit cold start).
+	ps1-meta -unity_root $src_c -metadata $path_atom_metadata -out_root $path_build_gen -passes @('--post-link') ` -extra_args @('--elf', $elf)
+
+	$dwarfLineBin     = join-path $path_build_gen 'hello_joypad.dwarf_line.bin'
+	$dwarfArangesBin  = join-path $path_build_gen 'hello_joypad.dwarf_aranges.bin'
+	$dwarfRnglistsBin = join-path $path_build_gen 'hello_joypad.dwarf_rnglists.bin'
+	$injectElf        = join-path $path_build 'hello_joypad.dwarf-injected.elf'
+	if ((Test-Path $dwarfLineBin) -and (Test-Path $dwarfArangesBin) -and (Test-Path $dwarfRnglistsBin))
+	{
+		Write-Host "[build] DWARF-injecting $elf -> $injectElf"
+		Copy-Item -LiteralPath $elf -Destination $injectElf -Force
+		# Objcopy call: 3x --update-section for (line, aranges, rnglists).
+		$f_args = @(
+			"--update-section=.debug_line=$dwarfLineBin",
+			"--update-section=.debug_aranges=$dwarfArangesBin",
+			"--update-section=.debug_rnglists=$dwarfRnglistsBin"
+		)
+		& $Objcopy @f_args $injectElf 2>&1 | Out-Null
+		if ($LASTEXITCODE -ne 0) {
+			Write-Warning "[build] objcopy F' splice failed (exit $LASTEXITCODE); removing $injectElf"
+			Remove-Item -LiteralPath $injectElf -ErrorAction SilentlyContinue
+			return;
+		}
+
+		$dwarfInfoBin     = join-path $path_build_gen 'hello_joypad.dwarf_info.bin'
+		$dwarfAbbrevBin   = join-path $path_build_gen 'hello_joypad.dwarf_abbrev.bin'
+		$dwarfStrBin      = join-path $path_build_gen 'hello_joypad.dwarf_str.bin'
+		$dwarfLocBin      = join-path $path_build_gen 'hello_joypad.dwarf_loc.bin'
+		$dwarfLoclistsBin = join-path $path_build_gen 'hello_joypad.dwarf_loclists.bin'
+		$g_args = @(
+			"--update-section=.debug_info=$dwarfInfoBin",
+			"--update-section=.debug_abbrev=$dwarfAbbrevBin",
+			"--update-section=.debug_str=$dwarfStrBin",
+			"--add-section=.debug_loc=$dwarfLocBin",
+			"--add-section=.debug_loclists=$dwarfLoclistsBin"
+		)
+		& $Objcopy @g_args $injectElf 2>&1 | Out-Null
+		if ($LASTEXITCODE -ne 0) {
+			Write-Warning "[build] objcopy G' splice failed (exit $LASTEXITCODE); removing $injectElf"
+			Remove-Item -LiteralPath $injectElf -ErrorAction SilentlyContinue
+			return;
+		}
+
+		# Baked atoms execute from RAM but are emitted as C data arrays, so their ELF sections lack SHF_EXECINSTR.
+		# GDB discards line rows for non-code sections. Mark only the debug-copy sections executable.
+		# The original ELF and PS-EXE remain byte/flag unchanged.
+		& $Objcopy `
+			--set-section-flags ".rodata=alloc,load,readonly,code,contents" `
+			--set-section-flags ".data=alloc,load,data,code,contents" `
+			$injectElf 2>&1 | Out-Null
+		if ($LASTEXITCODE -ne 0) {
+			Write-Warning "[build] atom-section flag update failed (exit $LASTEXITCODE); removing $injectElf"
+			Remove-Item -LiteralPath $injectElf -ErrorAction SilentlyContinue
+		} 
+		else {
+			Write-Host "[build] DWARF-injected ELF: $injectElf"
+		}
+	}
+}
+build-hello_joypad
 
 # NO idea if this works yet...
 function Send-ToEmulator { param( [string]$exePath )

scripts/duffle.lua

@@ -1180,10 +1180,9 @@ M.GTE_COMMAND_INPUTS = {
 --   * "mac_result"       : generic MAC output (nclip, op, mvmva)
 --
 -- Consumers:
---   * passes/static_analysis.lua::analyze_hardware_relations (the walker reads this after a GTE command to update
+--   * passes/static_analysis.lua::analyze_hardware_relations (the walker reads this after a GTE command to update `forward_state.post_command_roles` for `gte_role_mismatch`).
---     `forward_state.post_command_roles` for `gte_result_position`).
+--   * passes/static_analysis.lua::check_gte_role_mismatch (per-atom CHECK_RULES reader; renders role mismatches).
---   * passes/static_analysis.lua::check_gte_result_position (per-atom CHECK_RULES reader; renders role mismatches).
+-- This table is consumed by the hardware-relation analyzer and the gte_role_mismatch check.
--- This table is consumed by the hardware-relation analyzer and result-position check.
 M.GTE_COMMAND_OUTPUTS = {
 	-- RTPS: writes one screen coordinate (the perspective-divide result) into C2_SXY2.
 	-- The FIFO side effects leave SXY0 / SXY1 untouched, so `latest_screen_xy` is C2_SXY2.
@@ -1293,32 +1292,8 @@ M.GTE_COMMAND_LATCH_WINDOWS = {
 	},
 }
 
--- GTE component result contracts (immutable; keyed by bare component name).
+-- GTE component result contracts were removed: the `_post_<cmd>` naming convention was a soft convention
---
+-- (the user did not want it formalized via static-analysis enforcement). A proper `atom_info` directive for ordering semantics is a future TODO.
--- Register-role claims that the `_post_<cmd>` suffix alone cannot infer live here.
--- The bare name (the component name stripped of the `_post_<cmd>` suffix) is the key; the row carries the expected
--- command, the expected role, and the expected C2 register.
---
--- Known rows:
---   * `gte_store_g4_p3_post_rtps`: post-RTPS polygon-emit slot reads the newest projected screen coordinate from C2_SXY2.
---     C2_SXY0 is wrong (C2_SXY0 is an older FIFO entry, never the newest post-RTPS result).
---
--- Unknown `_post_<cmd>` components (a `<name>_post_<cmd>`-suffixed component whose bare `<name>` is not a row key) emit one
--- `table_gap` info finding so downstream consumers can detect when the contract table is incomplete for an authored atom body.
---
--- Consumers:
---   * passes/static_analysis.lua::check_gte_result_position (renders result-position findings).
---   * passes/static_analysis.lua::emit_table_gap_warning    (called once per atom body; surfaces the missing-row diagnostic).
--- This table is consumed by the result-position check.
-M.GTE_COMPONENT_RESULT_CONTRACTS = {
-	-- Post-RTPS g4 p3 store contract: writes the latest screen XY (C2_SXY2) into the primitive's p3 slot.
-	-- Reading from C2_SXY0 is a semantic mismatch — C2_SXY0 is the oldest post-RTPS SXY, not the newest one.
-	["gte_store_g4_p3_post_rtps"] = {
-		command  = "gte_cmdw_rtps",
-		role     = "latest_screen_xy",
-		register = "C2_SXY2",
-	},
-}
 
 -- Operand-class table for the COP2->GPR load-delay check.
 --
@@ -1447,6 +1422,7 @@ M.GP0_CMD_BY_SHAPE = {
 	["g4"]  = 0x38, ["gt4"] = 0x3C,
 }
 
+-- TODO(Ed): REMOVE THIS HARDCODE, THIS SHOULD BE RESOLVED AUTOMATICALLY
 -- Per-macro prim-buffer contribution: how many 32-bit words each macro writes to the primitive being built in main RAM.
 -- (This counts RAM-side prim-buffer words, not .text instruction words.)
 -- The sum across `mac_format_X_color` + `mac_gte_store_X_post_*` + `mac_insert_ot_tag_X` calls in an atom body must equal
@@ -1455,10 +1431,10 @@ M.GP0_MACRO_CONTRIB = {
 	["mac_format_f3_color"]      = 1,
 	["mac_format_g3_color"]      = 3,
 	["mac_format_g4_color"]      = 4,
-	["mac_gte_store_f3_post_rtpt"]                  = 3,
+	["mac_gte_store_f3"]         = 3,
-	["mac_gte_store_g3_post_rtpt"]                  = 3,
+	["mac_gte_store_g3"]         = 3,
-	["mac_gte_store_g4_p012_post_rtpt_pre_rtps"]    = 3,
+	["mac_gte_store_g4_p012"]    = 3,
-	["mac_gte_store_g4_p3_post_rtps"]               = 1,
+	["mac_gte_store_g4_p3"]      = 1,
 	["mac_insert_ot_tag_f3"]     = 1,
 	["mac_insert_ot_tag_g4"]     = 1,
 }
@@ -1583,6 +1559,8 @@ M.INSTRUCTION_LATENCY = {
 	["gte_load_v1"]         = 2,
 	["gte_load_v2"]         = 2,
 	["gte_load_v0v1v2"]     = 6,
+
+	-- TODO(Ed): REMOVE THIS HARDCODE, THIS SHOULD BE RESOLVED AUTOMATICALLY
 	-- mac_* helpers (cycle cost = sum of the expanded instructions)
 	-- mac_yield transfers control; cycle budget is 0 (the next atom absorbs the cost).
 	["mac_yield"]              = 0,
@@ -1591,12 +1569,13 @@ M.INSTRUCTION_LATENCY = {
 	["mac_format_g4_color"]    = 12, -- 4 x mac_pack_color_word
 	["mac_load_tri_indices"]   = 3,  -- 3 x lhu
 	["mac_gte_load_tri_verts"] = 18, -- 3 x {sll, addu, lw, lw, mtc2, mtc2}
-	["mac_gte_store_f3_post_rtpt"]               = 3,
+	["mac_gte_store_f3"]       = 3,
-	["mac_gte_store_g3_post_rtpt"]               = 3,
+	["mac_gte_store_g3"]       = 3,
-	["mac_gte_store_g4_p012_post_rtpt_pre_rtps"] = 3,
+	["mac_gte_store_g4_p012"]  = 3,
-	["mac_gte_store_g4_p3_post_rtps"]            = 1,
+	["mac_gte_store_g4_p3"]    = 1,
 	["mac_insert_ot_tag_f3"]   = 11,  -- 11 .word slots in the macro body
 	["mac_insert_ot_tag_g4"]   = 11,
+
 	-- Annotation markers (emit no code; pure metaprogram hints)
 	["atom_label"]          = 0,
 	["atom_offset"]         = 0,

scripts/gdb/gdb_tape_atoms.gdb

@@ -3,16 +3,16 @@
 # Wrapper for the tape-atom step-debug helpers.
 # The 9 user commands are defined here as STUBS (degraded-state messages). 
 # The real implementations + the per-atom data tables are emitted by `passes/atoms_source_map.lua` 
-# (post-link invocation: `ps1_meta.lua --atoms-source-map --gdb-runtime --elf <elf>`) into `build/gen/gdb_tape_atoms_runtime.gdb`.
+# (post-link invocation: `ps1_meta.lua --atoms-source-map --gdb-runtime --elf <elf>`) into `build/gdb_tape_atoms_runtime.gdb`.
 # Sourcing that file RE-DEFINES the commands with real implementations.
 #
-# If `build/gen/gdb_tape_atoms_runtime.gdb` is missing or stale, the stubs remain (E1: no source map).
+# If `build/gdb_tape_atoms_runtime.gdb` is missing or stale, the stubs remain (E1: no source map).
 # The user just needs to re-run `build_psyq.ps1` to regenerate.
 
-# ── Stub commands (defined here so they're always present, even if the runtime file is missing). The runtime file overrides these if sourced. ──
+# ?? Stub commands (defined here so they're always present, even if the runtime file is missing). The runtime file overrides these if sourced. ??
 
 define tape_atoms
-  echo "[gdb_tape_atoms] STUB: runtime file build/gen/gdb_tape_atoms_runtime.gdb not found."
+  echo "[gdb_tape_atoms] STUB: runtime file build/gdb_tape_atoms_runtime.gdb not found."
   echo "[gdb_tape_atoms] STUB: run .\\build_psyq.ps1 to regenerate, then re-source this file."
 end
 document tape_atoms
@@ -21,35 +21,35 @@ document tape_atoms
 end
 
 define break_atom
-  echo "[gdb_tape_atoms] STUB: build/gen/gdb_tape_atoms_runtime.gdb not sourced. Run build_psyq.ps1."
+  echo "[gdb_tape_atoms] STUB: build/gdb_tape_atoms_runtime.gdb not sourced. Run build_psyq.ps1."
 end
 document break_atom
   Set a breakpoint at the start of tape atom <name>. STUB state.
 end
 
 define step_atom
-  echo "[gdb_tape_atoms] STUB: build/gen/gdb_tape_atoms_runtime.gdb not sourced. Run build_psyq.ps1."
+  echo "[gdb_tape_atoms] STUB: build/gdb_tape_atoms_runtime.gdb not sourced. Run build_psyq.ps1."
 end
 document step_atom
   Resume execution until the next atom boundary. STUB state.
 end
 
 define next_atom
-  echo "[gdb_tape_atoms] STUB: build/gen/gdb_tape_atoms_runtime.gdb not sourced. Run build_psyq.ps1."
+  echo "[gdb_tape_atoms] STUB: build/gdb_tape_atoms_runtime.gdb not sourced. Run build_psyq.ps1."
 end
 document next_atom
   Alias for step_atom. STUB state.
 end
 
 define where_in_atom
-  echo "[gdb_tape_atoms] STUB: build/gen/gdb_tape_atoms_runtime.gdb not sourced. Run build_psyq.ps1."
+  echo "[gdb_tape_atoms] STUB: build/gdb_tape_atoms_runtime.gdb not sourced. Run build_psyq.ps1."
 end
 document where_in_atom
   Report current atom name, .rodata addr, word offset, and source line (if known). STUB state.
 end
 
 define stepi_inside_atom
-  echo "[gdb_tape_atoms] STUB: build/gen/gdb_tape_atoms_runtime.gdb not sourced. Run build_psyq.ps1."
+  echo "[gdb_tape_atoms] STUB: build/gdb_tape_atoms_runtime.gdb not sourced. Run build_psyq.ps1."
 end
 document stepi_inside_atom
   One MIPS-instruction step, then where_in_atom. STUB state.
@@ -89,17 +89,17 @@ document wave_ctx
 end
 
 
-# ── Source the runtime file (re-defines commands with real impls + data). ──
+# ?? Source the runtime file (re-defines commands with real impls + data). ??
 
 # Try to source from project-root-relative path first (the typical case).
 # If the user is in a different CWD, the source will fail and stubs remain.
-# The runtime file path is computed relative to the ELF's source map convention (build/gen/gdb_tape_atoms_runtime.gdb).
+# The runtime file path is computed relative to the ELF's source map convention (build/gdb_tape_atoms_runtime.gdb).
 echo [gdb_tape_atoms] Wrapper loaded. Sourcing runtime file...
 # Suppress the "Redefine command" prompts that would otherwise appear when the runtime file overrides the 9 stub commands defined above.
-# The runtime's `define` blocks are intended to overwrite — there's no ambiguity to confirm.
+# The runtime's `define` blocks are intended to overwrite ? there's no ambiguity to confirm.
 set confirm off
 
 # Source the runtime file (re-defines commands with real impls + data).
-source build/gen/gdb_tape_atoms_runtime.gdb
+source build/gdb_tape_atoms_runtime.gdb
 set confirm on
 echo [gdb_tape_atoms] Runtime sourced successfully (9 commands now have real implementations).

scripts/passes/annotation.lua

@@ -7,18 +7,11 @@
 ---
 --- Ownership: the canonical `ctx.shared.corpus` supplies cross-source registries, while each `src.scan` supplies its source's declarations and bodies.
 --- A context without `ctx.shared.corpus` is rejected with an explicit canonical-corpus message.
----
---- Writes `<ctx.out_root>/<dir_basename>.errors.h` once per module, with `#error` directives for findings that the C compile surfaces.
---- `passes/report.lua` renders annotations.txt from `corpus.sources_by_dir`, re-validating each source through `M.validate()`.
----
---- **Conventions**: tabs (1/level), EmmyLua annotations, no regex, Lua 5.3 compatible.
 
 -- Bootstrap follows the entry scripts; `scripts/duffle_paths.lua` sets package.path and package.cpath. See `ps1_meta.lua` for the rationale.
 -- `debug.getinfo(1, "S").source` locates this file for standalone and orchestrated runs, then `duffle_paths.lua` returns the loaded `duffle` module.
 local _bootstrap_dir = debug.getinfo(1, "S").source:match("^@?(.*[/\\])") or "./"
 local duffle         = dofile(_bootstrap_dir .. "../duffle_paths.lua")
-local write_file     = duffle.write_file
-local ensure_dir     = duffle.ensure_dir
 
 -- The annotation pass reads the source-derived registries from scan_source:
 --   * pipe_ctx.register_alias_registry — for atom_dbg_reg_default(R_X, ...) and atom_reg_types(R_X, ...) member-identity checks
@@ -605,40 +598,6 @@ local function validate(ctx, src, corpus_pipe_ctx)
 	}
 end
 
--- ════════════════════════════════════════════════════════════════════════════
--- Per-DIRECTORY (per-module) output: errors.h + annotations.txt
--- ════════════════════════════════════════════════════════════════════════════
-
---- Render `<dir_basename>.errors.h` with `#error` directives for every error found across all sources in the directory.
---- Empty directories (no errors, no atoms) produce no file.
-local function emit_module_errors_h(ctx, dir_basename, atoms_count, errors, sources)
-	if atoms_count == 0 and #errors == 0 then
-		return nil
-	end
-	local out_path = ctx.out_root .. "/" .. dir_basename .. ".errors.h"
-	local lines    = {
-		"// Auto-generated by ps1_meta.lua (passes/annotation.lua) — DO NOT EDIT",
-		string.format("// Module: %s   Sources: %d", dir_basename, #sources),
-		"#pragma once",
-		"",
-	}
-	if #errors == 0 then
-		lines[#lines + 1] = "// annotation pass OK"
-	else
-		for _, e in ipairs(errors) do
-			local src_tag = ""
-			if e.source then
-				local src_name = e.source:match("([^/\\]+)$") or e.source
-				src_tag = src_name .. ": "
-			end
-			lines[#lines + 1] = string.format('#error "%s%s (line %d)"', src_tag, e.msg, e.line)
-		end
-	end
-	ensure_dir(ctx.out_root)
-	write_file(out_path, table.concat(lines, "\n") .. "\n")
-	return out_path
-end
-
 -- ════════════════════════════════════════════════════════════════════════════
 -- M.run — orchestrator entry
 -- ════════════════════════════════════════════════════════════════════════════
@@ -683,11 +642,6 @@ function M.run(ctx)
 				warnings    [#warnings     + 1] = { line = w.line, msg = w.msg }
 			end
 		end
-
-		local err_path = emit_module_errors_h(ctx, dir_basename, dir_atoms, dir_errors, dir_sources)
-		if err_path then
-			table.insert(outputs, { errors_h = err_path })
-		end
 	end
 
 	return { outputs = outputs, errors = errors, warnings = warnings }

scripts/passes/atoms_source_map.lua

@@ -4,20 +4,18 @@
 --- `passes/dwarf_injection.lua` (synthesizes DW_TAG_inlined_subroutine + per-word line program rows) and the gdb-runtime
 --- wrapper at `scripts/gdb/gdb_tape_atoms.gdb` (loads the source map via `source <path>`).
 ---
---- Inputs from `atom.paths`: the ordered `items` stream, dense `word_events`, `invocations` views. Outputs: one
+--- Inputs from `atom.paths`: the ordered `items` stream, dense `word_events`, `invocations` views. Outputs: 
---- `WORD N LINE L TEXT T` line per emitted `.word`, plus the per-word provenance form that DWARF synthesis consumes.
+---  one `WORD N LINE L TEXT T` line per emitted `.word`, plus the per-word provenance form that DWARF synthesis consumes.
 ---
---- **Two output forms** (per the workspace's per-emission-form pattern from `guide_metaprogram_ssdl.md`):
+--- Two output forms:
----   1. **Sourcemap.txt form** — `<out_root>/<basename>.atoms.sourcemap.txt`. Format-version-tagged for forward-compat.
+---   1. Markdown form: Handled by `passes/report.lua` (writes `<module>.atoms.md`).
----      Lives in `<out_root>/` (build/gen). Mirrors the convention used by `annotation.lua`
+---      The render functions `render_source_map` + `render_provenance` are exported for `report.lua` to call directly.
----      (`<out_root>/<basename>.errors.h`) and `static_analysis.lua` (`<out_root>/<basename>.static_analysis.txt`).
 ---      Compile artifacts (`*.macs.h`, `*.offsets.h`) stay in `<source_dir>/gen/`.
----   2. **gdb-runtime form** — `<ctx.out_root>/gdb_tape_atoms_runtime.gdb`. A pure gdb command script — addresses come
+---   2. `gdb_tape_atoms_runtime.gdb`: Post-link opt-in (`ctx.flags.gdb_runtime`),
----      from `nm`, the 9 user commands are static `define ... end` blocks. Emitted when `ctx.flags.gdb_runtime` is true
+---      so the gdb wrapper script + the generated runtime script share the same canonical location.
----      AND `ctx.flags.elf_path` points to an existing ELF. Useful for `gdb-multiarch --without-python` users
+---      Triggered by `--post-link` or `--gdb-runtime`.
----      (the common case on Windows MinGW builds) — `source <path>` loads it with no Python / Tcl / Guile required.
 ---
---- **Output format** (sourcemap.txt form):
+--- Output forma (sourcemap.txt form):
 ---   ```
 ---   # FORMAT_VERSION 1
 ---   # auto-generated by ps1_meta.lua (passes/atoms_source_map.lua) — DO NOT EDIT
@@ -32,8 +30,6 @@
 ---   ```
 ---
 --- Marker records are zero-width in `atom.paths.items`, so they emit no WORD rows in the dense word view.
----
---- **Conventions:** tabs (1/level), EmmyLua annotations, no regex, Lua 5.3 compatible.
 
 -- ════════════════════════════════════════════════════════════════════════════
 -- Module-scope requires + package.path setup
@@ -458,7 +454,22 @@ local function emit_gdb_runtime(ctx)
 	-- Confirmation line for the source operator.
 	lines[#lines + 1] = 'printf "[gdb_tape_atoms] runtime loaded %d atoms from %s\\n", $__atom_count, $__elf_path'
 
-	local out_path = ctx.out_root .. "/gdb_tape_atoms_runtime.gdb"
+	local out_path
+	-- Move out of `<out_root>/gdb_tape_atoms_runtime.gdb` to `<out_root>/../gdb_tape_atoms_runtime.gdb` when the conventional `<out_root>` is `<build>/gen`
+	-- (any equivalent spelling — relative, absolute backslash, absolute forward-slash, trailing-separator variants).
+	-- This puts the gdb runtime alongside the ELF at `build/` rather than under the report subdir.
+	local function ends_with_gen_dir(p)
+		if type(p) ~= "string" then return false end
+		return p:match("[/\\]gen[/\\]?$") ~= nil or p == "build/gen" or p == "build\\gen"
+	end
+	if ends_with_gen_dir(ctx.out_root) then
+		-- Strip the trailing `/gen` segment, then write the runtime script under `build/`.
+		-- e.g. "C:/projects/Pikuma/ps1/build/gen" -> "C:/projects/Pikuma/ps1/build".
+		local parent = ctx.out_root:gsub("[/\\]gen[/\\]?$", "")
+		out_path = parent .. "/gdb_tape_atoms_runtime.gdb"
+	else
+		out_path = ctx.out_root .. "/gdb_tape_atoms_runtime.gdb"
+	end
 	duffle.ensure_dir(duffle.dirname(out_path))
 	duffle.write_file_lf(out_path, table.concat(lines, "\n") .. "\n")
 	-- io.stderr:write(string.format("[atoms_source_map] wrote %s (%d atoms)\n", out_path, #matched))
@@ -470,10 +481,62 @@ end
 
 local M = {}
 
---- Pass entry. For each source that declares at least one `MipsAtom_(name)` / `MipsCode code_<name>`, emit two files
+-- Expose the pure render functions so `report.lua` and the focused tests can call them directly without triggering the file-emit path.
---- in `<out_root>/`: `<basename>.atoms.sourcemap.txt` (per-word call-site map) and `<basename>.atoms.provenance.txt`
+M.render_source_map = render_source_map
---- (per-word definition + body line, resolved via the outermost `mac_X(...)` invocation). When `ctx.flags.gdb_runtime`
+M.render_provenance = render_provenance
---- is true and `ctx.flags.elf_path` exists, also emit the post-link gdb script `<ctx.out_root>/gdb_tape_atoms_runtime.gdb`.
+
+--- Render ONE atom's sourcemap stanza.
+--- @param atom table   -- atom record (must have `atom.paths` populated)
+--- @return string
+function M.render_atom_source_map(atom)
+	assert(type(atom) == "table", "render_atom_source_map: atom must be a table")
+	assert(type(atom.paths) == "table", "render_atom_source_map: atom.paths must be a table")
+	local entries, total = canonical_word_entries(atom)
+	local lines = {}
+	lines[#lines + 1] = string.format("ATOM %s  %d", (atom.raw_name or atom.name), total)
+	for _, entry in ipairs(entries) do
+		lines[#lines + 1] = string.format("WORD %d  LINE %d  TEXT %s",
+			entry.pos, entry.line, entry.text)
+	end
+	lines[#lines + 1] = "ENDATOM"
+	return table.concat(lines, "\n") .. "\n"
+end
+
+--- Render ONE atom's provenance stanza — no per-file format header, no enumeration of other atoms.
+---
+--- `rel_path` is the source path (forward-slashes) embedded in every `CALL` line.
+--- The .md caller (report.lua) is expected to derive this once per `## <source>` heading and pass it down for each atom in that source.
+--- @param atom      table   -- atom record (must have `atom.paths` populated)
+--- @param wc        table   -- identity alias of `corpus.word_counts`
+--- @param rel_path  string  -- source path (forward-slashes) for `CALL` fields
+--- @return string
+function M.render_atom_provenance(atom, wc, rel_path)
+	assert(type(atom)       == "table", "render_atom_provenance:  atom must be a table")
+	assert(type(atom.paths) == "table", "render_atom_provenance:  atom.paths must be a table")
+	assert(type(rel_path)   == "string", "render_atom_provenance: rel_path must be a string")
+	local entries, total = canonical_word_entries(atom)
+	local lines = {}
+	lines[#lines + 1] = string.format("ATOM %s  %d", (atom.raw_name or atom.name), total)
+	for _, entry in ipairs(entries) do
+		local inv = entry.invocation
+		local macro_count = inv and wc and wc["mac_" .. inv.component_name]
+		if inv and macro_count ~= nil then
+			lines[#lines + 1] = string.format(
+				'WORD %d  CALL %s:%d  MACRO %s "%s:%d" BODY %d',
+				entry.pos, rel_path, entry.line, inv.component_name,
+				inv.def_path or "", inv.def_line or 0, entry.body_line)
+		else
+			lines[#lines + 1] = string.format(
+				"WORD %d  CALL %s:%d  RAW", entry.pos, rel_path, entry.line)
+		end
+	end
+	return table.concat(lines, "\n") .. "\n"
+end
+
+--- Pass entry. For each source that declares at least one `MipsAtom_(name)` / `MipsCode code_<name>`,
+--- emit two files in `<out_root>/`: `<basename>.atoms.sourcemap.txt` (per-word call-site map) and `<basename>.atoms.provenance.txt`
+--- (per-word definition + body line, resolved via the outermost `mac_X(...)` invocation).
+--- When `ctx.flags.gdb_runtime` is true and `ctx.flags.elf_path` exists, also emit the post-link gdb script `<ctx.out_root>/gdb_tape_atoms_runtime.gdb`.
 --- @param ctx PassCtx
 --- @return PassResult
 function M.run(ctx)
@@ -495,34 +558,8 @@ function M.run(ctx)
 		}
 	end
 
-	-- Always emit the text form (per-source).
+	-- atoms.sourcemap.txt + atoms.provenance.txt content moved to report.lua via `<module>.atoms.md` markdown file.
-	for _, src in ipairs(corpus.source_order) do
+	-- This pass emits only the post-link gdb_runtime artifact (see emit_gdb_runtime below).
-		local has_projection = false
-		for _, atom in ipairs((src.scan or {}).atoms or {}) do
-			if (atom.kind == "atom" or atom.kind == "raw_atom") and atom.paths then
-				has_projection = true; break
-			end
-		end
-		if not has_projection then
-			for _, atom in ipairs((src.scan or {}).raw_atoms or {}) do
-				if atom.paths then has_projection = true; break end
-			end
-		end
-		if has_projection then
-			local basename = duffle.basename_no_ext(src.path)
-			-- (1) atoms.sourcemap.txt — format-1 per-word call-site map.
-			local sourcemap_path = ctx.out_root .. "/" .. basename .. ".atoms.sourcemap.txt"
-			local sourcemap_body = render_source_map(src)
-			-- (2) atoms.provenance.txt — format-1 per-word definition/body map.
-			local prov_path = ctx.out_root .. "/" .. basename .. ".atoms.provenance.txt"
-			local prov_body = render_provenance(src, wc)
-			duffle.ensure_dir(duffle.dirname(sourcemap_path))
-			duffle.write_file_lf(sourcemap_path, sourcemap_body)
-			duffle.write_file_lf(prov_path,    prov_body)
-			outputs[#outputs + 1] = { kind = "report", path = sourcemap_path }
-			outputs[#outputs + 1] = { kind = "report", path = prov_path }
-		end
-	end
 
 	-- Optionally emit the gdb-runtime form (post-link, one file per build).
 	if ctx.flags and ctx.flags.gdb_runtime then

scripts/passes/dwarf_injection.lua

@@ -153,6 +153,7 @@ local DW_AT_inline           = 0x20   -- DWARF5 §7.7.1: DW_AT_inline (used by a
 local DW_AT_decl_file        = 0x3A   -- DWARF5 §7.7.1: DW_AT_decl_file (1-based file index into the CU's file table)
 local DW_AT_decl_line        = 0x3B   -- DWARF5 §7.7.1: DW_AT_decl_line
 
+-- TODO(Ed): Remove this HARDCODE
 -- File index lookup table for the existing main line unit (Unit 2).
 -- Provenance paths come back with mixed slashes; we normalize to basename and look up against the line unit's actual file table.
 -- Current scope has two provenance basenames: hello_gte_tape.c (the atom's call site) and lottes_tape.h (the component definition).
@@ -162,7 +163,8 @@ local DW_AT_decl_line        = 0x3B   -- DWARF5 §7.7.1: DW_AT_decl_line
 -- headers that are pure macros/typedefs (dsl.h, memory.h, math.h, mips.h, gp.h, gte.h, etc.) never appear.
 -- lottes_tape.h is the FIRST include that emits line entries (MipsAtomComp_ declarations), so it is the FIRST entry after the primary file.
 local PROVENANCE_BASENAME_TO_FILE_INDEX = {
-	["hello_gte_tape.c"] = ATOM_SOURCE_FILE_INDEX,  -- = 11
+	["hello_joypad.tape.c"] = ATOM_SOURCE_FILE_INDEX,  -- = 11
+	["hello_gte.tape.c"] = ATOM_SOURCE_FILE_INDEX,  -- = 11
 	["lottes_tape.h"]    = 2,
 }
 

scripts/passes/report.lua

@@ -7,9 +7,6 @@
 ---
 --- The annotation pass emits `errors.h` files per module and the canonical `corpus.sources_by_dir` projection groups sources by directory.
 --- This pass iterates the canonical dir projection directly and re-validates each source via `annotation.validate()` to get the detailed per-source results.
----
---- **Conventions**: tabs (1/level), EmmyLua annotations, no regex,
---- Lua 5.3 compatible.
 
 -- ════════════════════════════════════════════════════════════════════════════
 -- Module-scope requires + package.path setup
@@ -18,8 +15,7 @@
 -- Resolve `arg[0]` to an absolute-ish script directory so that `require("duffle")` resolves against `scripts/` regardless of CWD.
 -- Bootstrap: see `ps1_meta.lua` for the rationale.
 -- Bootstrap: load `scripts/duffle_paths.lua` (sets package.path + package.cpath).
--- Uses `debug.getinfo` to find this file's own directory, so it works
+-- Uses `debug.getinfo` to find this file's own directory, so it works both standalone and when require'd from the orchestrator.
--- both standalone and when require'd from the orchestrator.
 -- Bootstrap: load `duffle_paths.lua` via `debug.getinfo(1, "S").source` (works both standalone + when require'd).
 -- duffle_paths.lua sets package.path then returns `require("duffle")` at the bottom, so the dofile value IS the duffle module.
 local _bootstrap_dir = debug.getinfo(1, "S").source:match("^@?(.*[/\\])") or "./"
@@ -30,6 +26,11 @@ local duffle        = dofile(_bootstrap_dir .. "../duffle_paths.lua")
 -- that the report pass renders into the per-module `<dir_basename>.annotations.txt` output.
 local annotation = dofile(_bootstrap_dir .. "annotation.lua")
 
+-- Load atoms_source_map for the `render_source_map` / `render_provenance` module functions (used by `render_module_atoms_md` to produce `<module>.atoms.md` without re-walking source tokens).
+-- The pass itself emits no per-source files anymore; we only consume the two pure renderers here.
+-- Defined BEFORE the renderer functions below so their upvalues resolve to this local (not the global `atoms_source_map`, which is nil).
+local atoms_source_map = dofile(_bootstrap_dir .. "atoms_source_map.lua")
+
 -- ════════════════════════════════════════════════════════════════════════════
 -- Constants
 -- ════════════════════════════════════════════════════════════════════════════
@@ -44,8 +45,7 @@ local SECTION_HEADER_MACROS    = "── Macro word-count declarations ───
 local SECTION_HEADER_ERRORS    = "── Errors ──────────────────────────────────────────────"
 local SECTION_HEADER_WARNINGS  = "── Warnings ────────────────────────────────────────────"
 
--- Lua pattern that captures the basename (last path segment) of a
+-- Lua pattern that captures the basename (last path segment) of a forward- or back-slash separated path.
--- forward- or back-slash separated path.
 local BASENAME_PATTERN = "([^/\\]+)$"
 
 -- Debug flag name — set to truthy in `_G` to enable verbose logging.
@@ -148,328 +148,451 @@ local function source_basename(path)
 	return path:match(BASENAME_PATTERN) or path
 end
 
---- (internal) Format a single annotation entry as one rendered line.
+-- ════════════════════════════════════════════════════════════════════════════
---- @param a AnnotEntry
+-- Markdown renderers (consolidated-report-files refactor, 2026-07-26)
---- @param src_name string
+-- ════════════════════════════════════════════════════════════════════════════
+
+--- Render the thin project-wide summary (`build/atom_meta_report.summary.md`).
+--- @param all_results { module:string, atoms:integer, annots:integer, binds:integer,
+---                       macros:integer, findings:integer, errors:integer,
+---                       warnings:integer, info:integer }[]
 --- @return string
-local function format_annot_line(a, src_name)
+local function render_project_summary(all_results)
-	if a.error then
+	local lines = {
-		return string.format("  ✗ line %d  %s  [ERROR: %s]  [%s]", a.line, a.macro or "?", a.error, src_name)
+		"# Project summary",
+		"> Auto-generated by ps1_meta.lua (passes/report.lua).",
+		"",
+		"| module | atoms | annots | binds | macros | findings | errors | warnings | info |",
+		"|--------|-------|--------|-------|--------|----------|--------|----------|------|",
+	}
+	local totals = { atoms = 0, annots = 0, binds = 0, macros = 0,
+		findings = 0, errors = 0, warnings = 0, info = 0 }
+	for _, e in ipairs(all_results) do
+		lines[#lines + 1] = string.format(
+			"| %s | %d | %d | %d | %d | %d | %d | %d | %d |",
+			e.module, e.atoms, e.annots, e.binds, e.macros,
+			e.findings, e.errors, e.warnings, e.info)
+		totals.atoms    = totals.atoms    + e.atoms
+		totals.annots   = totals.annots   + e.annots
+		totals.binds    = totals.binds    + e.binds
+		totals.macros   = totals.macros   + e.macros
+		totals.findings = totals.findings + e.findings
+		totals.errors   = totals.errors   + e.errors
+		totals.warnings = totals.warnings + e.warnings
+		totals.info     = totals.info     + e.info
 	end
-	local line = string.format("  ●  line %d  %s  [%s]", a.line, a.name, src_name)
+	lines[#lines + 1] = string.format(
-	if a.binds       then line = line .. "  binds="   .. a.binds end
+		"| **TOTAL** | %d | %d | %d | %d | %d | %d | %d | %d |",
-	if #a.reads  > 0 then line = line .. "  reads={"  .. table.concat(a.reads,  ",") .. "}" end
+		totals.atoms, totals.annots, totals.binds, totals.macros,
-	if #a.writes > 0 then line = line .. "  writes={" .. table.concat(a.writes, ",") .. "}" end
+		totals.findings, totals.errors, totals.warnings, totals.info)
-	return line
+	return table.concat(lines, "\n") .. "\n"
 end
 
---- (internal) Tally totals across all results in a module.
+--- Render the per-module verbose source-map markdown (`build/<module>.atoms.md`).
---- @param results AnnotationResult[]
+--- Per-source sub-section, per-atom stanza with sourcemap + provenance rows.
---- @return integer, integer, integer, integer, integer, integer
+--- Pulls sourcemap + provenance from `atoms_source_map` (no second source walk).
-local function tally_module_totals(results)
+--- @param dir string
-	local total_atoms, total_annots, total_binds, total_macros = 0, 0, 0, 0
+--- @param dir_sources SourceFile[]
-	local total_errors, total_warnings = 0, 0
+--- @param wc table<string, integer>
-	for _, r in ipairs(results) do
+--- @return string
-		total_atoms    = total_atoms    + #r.atoms
+local function render_module_atoms_md(dir, dir_sources, wc)
-		total_annots   = total_annots   + #r.annots
+	local dir_basename = source_basename(dir)
-		total_binds    = total_binds    + #r.binds
+	local lines = {
-		total_macros   = total_macros   + #r.macros
+		"# " .. dir_basename .. " — atoms (verbose source map)",
-		total_errors   = total_errors   + #r.errors
+		"> Per-word call-site + provenance. Auto-generated.",
-		total_warnings = total_warnings + #r.warnings
+		"",
+	}
+	for _, src in ipairs(dir_sources) do
+		local src_name = source_basename(src.path)
+		lines[#lines + 1] = "## " .. src_name
+		lines[#lines + 1] = ""
+		-- For each atom with a projection, render its sourcemap + provenance.
+		local atoms_list = {}
+		for _, atom in ipairs((src.scan or {}).atoms or {}) do
+			if atom.paths then atoms_list[#atoms_list + 1] = atom end
 		end
-	return total_atoms, total_annots, total_binds, total_macros, total_errors, total_warnings
+		for _, atom in ipairs((src.scan or {}).raw_atoms or {}) do
+			if atom.paths then atoms_list[#atoms_list + 1] = atom end
+		end
+		if #atoms_list == 0 then
+			lines[#lines + 1] = "_(no atom projections)_"
+			lines[#lines + 1] = ""
+		else
+			-- Per-source forward-slash path (same one `emit_atom_stanza` / `emit_provenance_stanza` would derive;
+			-- computed once per `## <source>` heading and reused by each atom's `WORD N CALL ...` field).
+			local rel_path = src.path:gsub("\\\\", "/")
+			for _, atom in ipairs(atoms_list) do
+				lines[#lines + 1] = string.format(
+					"### atom: %s (line %d, %d words)",
+					atom.name, atom.line or 0, #(atom.paths.items or {}))
+				lines[#lines + 1] = ""
+				lines[#lines + 1] = "**Sourcemap** — per-word call site:"
+				lines[#lines + 1] = "```"
+				-- Per-atom invariant: call the per-atom renderers, NOT the per-source ones.
+				-- The per-source renderers enumerate every atom in `src`;
+				-- calling them in a per-atom loop would repeat the whole source under every `### atom:` heading.
+				lines[#lines + 1] = atoms_source_map.render_atom_source_map(atom):gsub("\n+$", "")
+				lines[#lines + 1] = "```"
+				lines[#lines + 1] = ""
+				lines[#lines + 1] = "**Provenance** — per-word definition + body:"
+				lines[#lines + 1] = "```"
+				lines[#lines + 1] = atoms_source_map.render_atom_provenance(atom, wc, rel_path):gsub("\n+$", "")
+				lines[#lines + 1] = "```"
+				lines[#lines + 1] = ""
+			end
+		end
+	end
+	return table.concat(lines, "\n") .. "\n"
 end
 
--- (internal) Section renderer: per-source atom declarations.
+--- Render the consolidated per-module markdown (`build/<module>.atom_meta_report.md`).
-local function render_module_atoms_section(add, results)
+--- Aggregates annotation + static-analysis content across all sources in `dir`.
-	add(SECTION_HEADER_ATOMS)
+--- Annotations come from re-running `annotation.validate()` per source (the existing pattern);
-	for _, r in ipairs(results) do
+--- static-analysis comes from `corpus.static_analysis_results[dir_basename]` (populated by `static_analysis.lua` — no second corpus_pipe_ctx build).
+--- @param dir string
+--- @param dir_sources SourceFile[]
+--- @param annot_results AnnotationResult[]
+--- @param sa_results table                 -- corpus.static_analysis_results[dir_basename]
+--- @return string
+local function render_module_meta_report(dir, dir_sources, annot_results, sa_results)
+	local dir_basename = source_basename(dir)
+	local lines = {
+		"# " .. dir_basename .. " — atom meta report",
+		"> Auto-generated by ps1_meta.lua (passes/report.lua). Do not edit.",
+		"",
+	}
+	local function add(s) lines[#lines + 1] = s end
+
+	-- Module summary table.
+	local n_atoms        = 0
+	local n_annot        = 0
+	local n_binds        = 0
+	local n_macros       = 0
+	local n_bare, n_proc = 0, 0
+	for _, r in ipairs(annot_results) do
+		n_atoms  = n_atoms  + #r.atoms
+		n_annot  = n_annot  + #r.annots
+		n_binds  = n_binds  + #r.binds
+		n_macros = n_macros + #r.macros
+	end
+	for _, a in ipairs(sa_results.atoms or {}) do
+		if     a.kind == "comp_bare" then n_bare = n_bare + 1
+		elseif a.kind == "comp_proc" then n_proc = n_proc + 1
+		end
+	end
+
+	add("## Module summary"); add("")
+	add("| metric | value |"); add("|--------|-------|")
+	add(string.format("| sources | %d |", #dir_sources))
+	add(string.format("| atoms | %d (atoms: %d, comp_bare: %d, comp_proc: %d) |",
+		#(sa_results.atoms or {}),
+		#(sa_results.atoms or {}) - n_bare - n_proc, n_bare, n_proc))
+	add(string.format("| annotations | %d |", n_annot))
+	add(string.format("| binds structs | %d |", n_binds))
+	add(string.format("| macro decls | %d |", n_macros))
+	add(string.format("| findings | %d (errors: %d, warnings: %d, info: %d) |",
+		#(sa_results.findings or {}),
+		#(sa_results.errors   or {}),
+		#(sa_results.warnings or {}),
+		#(sa_results.info     or {})))
+	add("")
+
+	-- Sources
+	add("## Sources"); add("")
+	for _, s in ipairs(dir_sources) do add("- `" .. s.path .. "`") end
+	add("")
+
+	-- Atoms (annotation)
+	add("## Atoms"); add("")
+	add("| kind | name | source | line |"); add("|------|------|--------|------|")
+	for _, r in ipairs(annot_results) do
 		local src_name = source_basename(r.source)
 		for _, a in ipairs(r.atoms) do
-			add(string.format("  MipsAtom_(%s)   line %d   [%s]", a.name, a.line, src_name))
+			add(string.format("| atom | %s | %s | %d |", a.name, src_name, a.line))
 		end
 	end
 	add("")
-end
 
--- (internal) Section renderer: per-source annotation entries.
+	-- Annotations
-local function render_module_annots_section(add, results)
+	add("## Annotations"); add("")
-	add(SECTION_HEADER_ANNOTS)
+	if #annot_results == 0 then
-	for _, r in ipairs(results) do
+		add("_(none)_")
+	else
+		add("| source | line | name | binds | reads | writes |")
+		add("|--------|------|------|-------|-------|--------|")
+		for _, r in ipairs(annot_results) do
 			local src_name = source_basename(r.source)
 			for _, a in ipairs(r.annots) do
-			add(format_annot_line(a, src_name))
+				local binds  = a.binds  or "—"
+				local reads  = (#a.reads  > 0 and table.concat(a.reads,  ",")) or "—"
+				local writes = (#a.writes > 0 and table.concat(a.writes, ",")) or "—"
+				add(string.format("| %s | %d | %s | %s | %s | %s |",
+					src_name, a.line, a.name, binds, reads, writes))
+			end
 		end
 	end
 	add("")
-end
 
--- (internal) Section renderer: per-source Binds_* struct declarations.
+	-- Binds_* structs
-local function render_module_binds_section(add, results)
+	add("## Binds_* structs"); add("")
-	add(SECTION_HEADER_BINDS)
+	if #annot_results == 0 then
-	for _, r in ipairs(results) do
+		add("_(none)_")
+	else
+		for _, r in ipairs(annot_results) do
 			local src_name = source_basename(r.source)
 			for _, b in ipairs(r.binds) do
-			add(string.format("  %s   line %d   %d bytes   [%s]", b.name, b.line, b.bytes, src_name))
+				add(string.format("### %s (%s:%d, %d bytes)",
+					b.name, src_name, b.line, b.bytes))
 				for _, f in ipairs(b.fields) do
-				add(string.format("    +%2d: %s", f.offset, f.name))
+					add(string.format("- `+%d %s`", f.offset, f.name))
-			end
-		end
 				end
 				add("")
 			end
+		end
+	end
 
--- (internal) Section renderer: per-source macro word-count declarations.
+	-- Macro decls
-local function render_module_macros_section(add, results)
+	add("## Macro word-count declarations"); add("")
-	add(SECTION_HEADER_MACROS)
+	if #annot_results == 0 then
-	for _, r in ipairs(results) do
+		add("_(none)_")
+	else
+		add("| source | line | macro declaration |")
+		add("|--------|------|-------------------|")
+		for _, r in ipairs(annot_results) do
 			local src_name = source_basename(r.source)
 			for _, m in ipairs(r.macros) do
-			add(string.format("  %s  line %d  words=%d  [%s]", m.name, m.line, m.words, src_name))
+				add(string.format("| %s | %d | %s |",
+					src_name, m.line, m.name))
+			end
 		end
 	end
 	add("")
-end
 
--- (internal) Section renderer: per-source errors (one-line + "(none)" if empty).
+	-- Findings by atom (static-analysis)
-local function render_module_errors_section(add, results, total_errors)
+	add("## Static analysis — findings by atom"); add("")
-	add(SECTION_HEADER_ERRORS)
+	local by_atom = {}
-	if total_errors == 0 then
+	for _, f in ipairs(sa_results.findings or {}) do
-		add("  (none)")
+		by_atom[f.atom] = by_atom[f.atom] or {}
+		by_atom[f.atom][#by_atom[f.atom] + 1] = f
+	end
+	if next(by_atom) == nil then
+		add("_(no findings)_")
 	else
-		for _, r in ipairs(results) do
+		for _, a in ipairs(sa_results.atoms or {}) do
-			local src_name = source_basename(r.source)
+			local fs = by_atom[a.name]
-			for _, e in ipairs(r.errors) do
+			if fs then
-				add(string.format("  ✗ line %d  %s  [%s]", e.line, e.msg, src_name))
+				add(string.format("### %s", a.name))
-			end
+				for _, f in ipairs(fs) do
-		end
+					add(string.format("- `[%s] %s`", f.check, f.msg))
 				end
 				add("")
 			end
+		end
+	end
 
--- (internal) Section renderer: per-source warnings (one-line + "(none)" if empty).
+	-- Errors / Warnings / Info
-local function render_module_warnings_section(add, results, total_warnings)
+	local function add_findings(label, entries)
-	add(SECTION_HEADER_WARNINGS)
+		add(string.format("## %s", label))
-	if total_warnings == 0 then
+		if #entries == 0 then
-		add("  (none)")
+			add("_(none)_")
 		else
-		for _, r in ipairs(results) do
+			for _, e in ipairs(entries) do
-			local src_name = source_basename(r.source)
+				add(string.format("- line %d  %s", e.line, e.msg))
-			for _, w in ipairs(r.warnings) do
-				add(string.format("  ⚠ line %d  %s  [%s]", w.line, w.msg, src_name))
-			end
 			end
 		end
 		add("")
 	end
+	add_findings("Errors",   sa_results.errors   or {})
+	add_findings("Warnings", sa_results.warnings or {})
+	add_findings("Info",     sa_results.info     or {})
 
--- ════════════════════════════════════════════════════════════════════════════
+	-- Per-atom cycle counts (path-aware)
--- SECTION_RENDERERS — data-driven section dispatch (the plex pattern)
+	add("## Per-atom cycle counts (path-aware, best case, no stalls)"); add("")
--- ════════════════════════════════════════════════════════════════════════════
+	add("| atom | source | min | max | branches | paths | notes |")
---
+	add("|------|--------|-----|-----|----------|-------|-------|")
--- Each entry maps a section to its (header, render_fn). The render_fn signature:
+	local sorted = {}
---   render_fn(add, results, totals)
+	for _, a in ipairs(sa_results.atoms or {}) do sorted[#sorted + 1] = a end
---     add    -- the `add(line)` closure from the surrounding report renderer
+	table.sort(sorted, function(x, y)
---     results -- AnnotationResult[] (per-source results)
+		return ((x.paths or {}).cycles_max or 0) > ((y.paths or {}).cycles_max or 0)
---     totals -- {atoms, annots, binds, macros, errors, warnings} counts
+	end)
---
+	for _, a in ipairs(sorted) do
--- Sections that need to render "(none)" vs iterate use totals.errors / totals.warnings;
+		local p        = a.paths or {}
--- other sections ignore the totals arg.
+		local src_name = a.source_path and source_basename(a.source_path) or ""
--- Adding a new section = 1 row here + 1 render_<thing>_section function.
+		local notes   = ""
-local SECTION_RENDERERS = {
+		if p.has_loops then notes = notes .. " [loop!]" end
-	{ header = SECTION_HEADER_ATOMS,    render = render_module_atoms_section     },
+		if p.unknown_macros and #p.unknown_macros > 0 then
-	{ header = SECTION_HEADER_ANNOTS,   render = render_module_annots_section    },
+			notes = notes .. " [unknown: " .. table.concat(p.unknown_macros, ", ") .. "]"
-	{ header = SECTION_HEADER_BINDS,    render = render_module_binds_section     },
-	{ header = SECTION_HEADER_MACROS,   render = render_module_macros_section    },
-	{ header = SECTION_HEADER_ERRORS,   render = function(add, results, totals) return render_module_errors_section(add, results, totals.errors)   end },
-	{ header = SECTION_HEADER_WARNINGS, render = function(add, results, totals) return render_module_warnings_section(add, results, totals.warnings) end },
-}
-
---- Render the per-MODULE annotation report (one `<dir_basename>.annotations.txt`).
---- @param dir string                  -- module directory path
---- @param sources SourceFile[]        -- sources in this module
---- @param results AnnotationResult[]  -- per-source validate() results
---- @return string                     -- the rendered report text
-local function render_module_report(dir, sources, results)
-	local lines = {}
-	local function add(s) lines[#lines + 1] = s end
-
-	add(RULE_THICK)
-	add("ANNOTATION PASS — module " .. source_basename(dir))
-	add(RULE_THICK)
-	add(string.format("Sources: %d", #sources))
-	for _, s in ipairs(sources) do add("  " .. s.path) end
-	add("")
-
-	local total_atoms, total_annots, total_binds, total_macros, total_errors, total_warnings = tally_module_totals(results)
-	add(string.format("Atoms: %d   Annotations: %d   Binds structs: %d   Macro decls: %d",
-		total_atoms, total_annots, total_binds, total_macros))
-	add("")
-
-	-- Bundle the totals so the section renderers don't need separate parameter lists.
-	-- Errors/warnings sections need their total count to decide "(none)" vs iterate.
-	-- Sections without totals (atoms/annots/binds/macros) ignore this arg.
-	local totals = {
-		atoms    = total_atoms,  annots = total_annots,  binds  = total_binds,
-		macros   = total_macros, errors = total_errors,  warnings = total_warnings,
-	}
-
-	-- THE per-section dispatch. ONE loop over SECTION_RENDERERS.
-	-- Each renderer writes its header + content via the `add` closure (pre-bound above).
-	-- Adding a new section = 1 row here + 1 render_<thing>_section function.
-	for _, section in ipairs(SECTION_RENDERERS) do
-		section.render(add, results, totals)
 		end
+		add(string.format("| %s | %s | %d | %d | %d | %d | %s |",
+			a.name, src_name,
+			p.cycles_min or 0, p.cycles_max or 0,
+			p.branches or 0, p.paths or 0, notes))
+	end
+	add("")
+
+	-- Per-source scan summary
+	add("## Per-source scan summary"); add("")
+	for _, src in ipairs(dir_sources) do
+		local src_atoms = {}
+		for _, a in ipairs(sa_results.atoms or {}) do
+			if a.source_path == src.path then src_atoms[#src_atoms + 1] = a end
+		end
+		if #src_atoms > 0 then
+			local mn, mx = math.huge, -1
+			for _, a in ipairs(src_atoms) do
+				local p = a.paths or {}
+				if (p.cycles_min or 0) < mn then mn = p.cycles_min or 0 end
+				if (p.cycles_max or 0) > mx then mx = p.cycles_max or 0 end
+			end
+			local path_str
+			if mx > 0 then
+				path_str = string.format("  cycles=%d..%d", mn, mx)
+			else
+				path_str = string.format("  %d cycles", mn)
+			end
+			add(string.format("- `%s` — %d atom%s%s",
+				src.basename, #src_atoms,
+				#src_atoms == 1 and "" or "s", path_str))
+		end
+	end
+	add("")
 
 	return table.concat(lines, "\n") .. "\n"
 end
 
 -- ════════════════════════════════════════════════════════════════════════════
--- Per-project summary
+-- REPORT_RENDERERS — data-driven report dispatch (one row per file kind)
 -- ════════════════════════════════════════════════════════════════════════════
-
+-- `once = true` means render once at the project level (not per-module).
---- Render the per-project summary (`build/gen/annotation_validation.txt`).
+-- `basename(dir_basename)` yields the file's basename for that kind.
---- Aggregates totals across all sources; lists per-source error counts if any source has errors.
+-- `gather(ctx, dir, dir_sources [, all_modules])` returns the rendered string.
---- @param all_results AnnotationResult[]
+local REPORT_RENDERERS = {
---- @return string
+	{
-local function render_project_report(all_results)
+		name     = "atom_meta_report",
-	local lines = {}
+		ext      = "md",
-	local function add(s) lines[#lines + 1] = s end
+		basename = function(dir_basename) return dir_basename .. ".atom_meta_report" end,
-
+		once     = false,
-	local total_atoms, total_annots, total_macros, total_binds = 0, 0, 0, 0
+		gather   = function(ctx, dir, dir_sources)
-	local total_errors, total_warnings = 0, 0
+			-- Annotations: re-run `annotation.validate()` per source (the existing pattern).
-	for _, r in ipairs(all_results) do
+			local annot_results = {}
-		total_atoms    = total_atoms    + #r.atoms
-		total_annots   = total_annots   + #r.annots
-		total_macros   = total_macros   + #r.macros
-		total_binds    = total_binds    + #r.binds
-		total_errors   = total_errors   + #r.errors
-		total_warnings = total_warnings + #r.warnings
-	end
-
-	add(RULE_THICK)
-	add("ANNOTATION VALIDATION — project summary")
-	add(RULE_THICK)
-	add("")
-	add(string.format("Atoms:        %d", total_atoms))
-	add(string.format("Annotations:  %d", total_annots))
-	add(string.format("Macros:       %d", total_macros))
-	add(string.format("Binds:        %d", total_binds))
-	add("")
-	add(string.format("Errors:       %d", total_errors))
-	add(string.format("Warnings:     %d", total_warnings))
-	add("")
-
-	if total_errors > 0 then
-		add("Per-source error counts:")
-		for _, r in ipairs(all_results) do
-			if #r.errors > 0 then
-				local src_name = source_basename(r.source)
-				add(string.format("  %s : %d error(s)", src_name, #r.errors))
-			end
-		end
-		add("")
-	end
-
-	return table.concat(lines, "\n") .. "\n"
-end
-
--- ════════════════════════════════════════════════════════════════════════════
--- Orchestration helpers
--- ════════════════════════════════════════════════════════════════════════════
-
---- (internal) Re-validate every source in a directory against the canonical corpus projection.
---- Calls `annotation.validate()` per source to produce the per-source AnnotationResult (atoms / annots / macros / binds / errors / warnings)
---- that the report renderer consumes. Eeach report pass run is reproducible from the corpus.
---- Returns the list of module results + the flat list of all results (for the project-wide summary).
---- @param ctx PassCtx
---- @param dir_sources SourceFile[]
---- @return AnnotationResult[], AnnotationResult[]
-local function lookup_module_results(ctx, dir_sources)
-	local module_results = {}
-	local all_results    = {}
 			for _, src in ipairs(dir_sources) do
 				if src.scan then
-			local result = annotation.validate(ctx, src, nil)
+					local r = annotation.validate(ctx, src, nil)
-			result.source = src.path                                    -- tag for downstream rendering
+					r.source = src.path
-			module_results[#module_results + 1] = result
+					annot_results[#annot_results + 1] = r
-			all_results[#all_results + 1] = result
-		end
-	end
-	return module_results, all_results
-end
-
---- (internal) Does this module's results contain anything worth emitting?
---- @param module_results AnnotationResult[]
---- @return boolean
-local function module_has_content(module_results)
-	for _, r in ipairs(module_results) do
-		if #r.atoms  > 0 or #r.annots > 0 or #r.binds    > 0
-		or #r.macros > 0 or #r.errors > 0 or #r.warnings > 0 then
-			return true
-		end
-	end
-	return false
-end
-
---- (internal) Log a debug message if `_G[DEBUG_FLAG]` is truthy.
---- @param fmt string
-local function debug_log(fmt, ...)
-	if _G[DEBUG_FLAG] then
-		io.stderr:write(string.format("[%s] " .. fmt, PASS_NAME, ...))
 				end
 			end
+			-- Static-analysis: read stashed projection (no re-validate).
+			local dir_basename = dir:match("([^/\\]+)$") or dir
+			local sa_results   = (ctx.shared.corpus.static_analysis_results or {})[dir_basename] or {}
+			return render_module_meta_report(dir, dir_sources, annot_results, sa_results)
+		end,
+	},
+	{
+		name     = "atoms",
+		ext      = "md",
+		basename = function(dir_basename) return dir_basename .. ".atoms" end,
+		once     = false,
+		gather   = function(ctx, dir, dir_sources)
+			return render_module_atoms_md(dir, dir_sources,
+				ctx.shared.corpus.word_counts or {})
+		end,
+	},
+	{
+		name     = "summary",
+		ext      = "md",
+		basename = function(_dir_basename) return "atom_meta_report.summary" end,
+		once     = true,
+		gather   = function(_ctx, _dir, _dir_sources, all_modules)
+			return render_project_summary(all_modules)
+		end,
+	},
+}
 
 -- ════════════════════════════════════════════════════════════════════════════
--- M — module exports
+-- M — public pass surface
 -- ════════════════════════════════════════════════════════════════════════════
 
 local M = {}
 
---- Run the report pass. 
+--- Run the report pass. Emits 1 `atom_meta_report.summary.md` per build + 2 `atom_meta_report.md` + 2 `atoms.md` files per module (duffle + gte_hello).
---- Renders one `<dir_basename>.annotations.txt` per source-directory that has content, plus the project-wide `annotation_validation.txt` summary.
+--- Reads `corpus.static_analysis_results` (added in Phase 1) to populate per-module findings without re-running validate().
 --- @param ctx PassCtx
 --- @return PassResult
 function M.run(ctx)
 	local outputs = {}
-	local errors   = {}
-	local warnings = {}
-
-	-- Module grouping comes from `corpus.sources_by_dir` (the canonical projection).
-	-- Iterate it directly; no private cache, no per-pass stash.
 	local corpus  = ctx.shared and ctx.shared.corpus
 	local by_dir  = (corpus and corpus.sources_by_dir) or {}
 
-	duffle.ensure_dir(ctx.out_root)
+	-- `out_path_root`: when the conventional `out_root` is `build/gen` (any spelling — relative, absolute, separator variants).
+	-- Write the md files to `build/` (parent of `gen/`) instead of nested under `gen/`.
+	-- Mirrors the `gdb_tape_atoms_runtime.gdb` relocation.
+	local function ends_with_gen(p)
+		return type(p) == "string" and (p:match("[/\\]gen[/\\]?$") ~= nil
+			or p == "build/gen" or p == "build\\gen")
+	end
+	local out_root_effective = ends_with_gen(ctx.out_root)
+		and ctx.out_root:gsub("[/\\]gen[/\\]?$", "")
+		or ctx.out_root
+
+	duffle.ensure_dir(out_root_effective)
+
+	-- Aggregator for the project-wide `once = true` summary renderer.
+	local all_modules = {}
 
-	local all_results_for_summary = {}
 	for dir, dir_sources in pairs(by_dir) do
 		local dir_basename = dir:match("([^/\\]+)$") or dir
-		debug_log("dir=%s basename=%s sources=%d\n", dir, dir_basename, #dir_sources)
 
-		if #dir_sources > 0 then
+		-- Per-renderer dispatch for the per-module renderers (once = false).
-			local module_results, all_results = lookup_module_results(ctx, dir_sources)
+		for _, renderer in ipairs(REPORT_RENDERERS) do
-			for _, r in ipairs(all_results) do
+			if not renderer.once then
-				all_results_for_summary[#all_results_for_summary + 1] = r
+				local body     = renderer.gather(ctx, dir, dir_sources)
-			end
+				local out_path = out_root_effective .. "/" .. renderer.basename(dir_basename) .. "." .. renderer.ext
-
+				duffle.write_file(out_path, body)
-			if module_has_content(module_results) then
+				outputs[#outputs + 1] = { kind = renderer.name, path = out_path }
-				local out_path = ctx.out_root .. "/" .. dir_basename .. ".annotations.txt"
-				duffle.write_file(out_path, render_module_report(dir, dir_sources, module_results))
-				outputs[#outputs + 1] = { annotations_txt = out_path }
-			else
-				debug_log("  -> no content; skipping\n")
-			end
 			end
 		end
 
-	if #all_results_for_summary > 0 then
+		-- For the summary, compute per-module totals once (re-validating annotations per source — same pattern as the meta_report renderer).
-		local summary_path = ctx.out_root .. "/annotation_validation.txt"
+		local annot_results = {}
-		duffle.write_file(summary_path, render_project_report(all_results_for_summary))
+		for _, src in ipairs(dir_sources) do
-		outputs[#outputs + 1] = { summary_txt = summary_path }
+			if src.scan then
+				local r = annotation.validate(ctx, src, nil)
+				r.source = src.path
+				annot_results[#annot_results + 1] = r
+			end
+		end
+		local n_annot, n_binds, n_macros = 0, 0, 0
+		for _, r in ipairs(annot_results) do
+			n_annot  = n_annot  + #r.annots
+			n_binds  = n_binds  + #r.binds
+			n_macros = n_macros + #r.macros
+		end
+		local sa_results = (corpus.static_analysis_results or {})[dir_basename] or {}
+		all_modules[#all_modules + 1] = {
+			module   = dir_basename,
+			atoms    = #(sa_results.atoms or {}),
+			annots   = n_annot,
+			binds    = n_binds,
+			macros   = n_macros,
+			findings = #(sa_results.findings or {}),
+			errors   = #(sa_results.errors   or {}),
+			warnings = #(sa_results.warnings or {}),
+			info     = #(sa_results.info     or {}),
+		}
 	end
 
-	return { outputs = outputs, errors = errors, warnings = warnings }
+	-- Project-wide renderer (once = true): write the summary file.
+	for _, renderer in ipairs(REPORT_RENDERERS) do
+		if renderer.once then
+			local body     = renderer.gather(ctx, nil, nil, all_modules)
+			local out_path = out_root_effective .. "/" .. renderer.basename("") .. "." .. renderer.ext
+			duffle.write_file(out_path, body)
+			outputs[#outputs + 1] = { kind = renderer.name, path = out_path }
+		end
+	end
+
+	return { outputs = outputs, errors = {}, warnings = {} }
 end
 
 return M

scripts/passes/static_analysis.lua

@@ -39,17 +39,19 @@
 --- The report header includes `Info: N` alongside Findings / Errors / Warnings, and a dedicated
 --- `── Info` section renders finding-level info between `── Warnings` and the per-atom cycle counts.
 ---
+--- The structural handshake checks (`mac_yield_uniformity`, `hazard_nop_use`, `control_transfer_delay_slot_use`) skip atoms/components with `debug_skip == true`.
+--- The `atom_dbg_skip` marker designates runtime-helper declarations whose structure is fixed by the tape runtime (e.g. `tape_exit`, `ac_yield`).
+--- Flagging them as "missing mac_yield" or "BD slot is redundant" is signal noise, not a logic failure. 
+--- Other checks (transfer_hazards, gpu_portstore_shape, abi_handoff, enum_alias_membership, …) still apply to debug_skip declarations because real hazards / typos can still surface in them.
+---
 --- The orchestrator (`ps1_meta.lua`) wires this module in via the PASSES table:
 ---   `["static-analysis"] = {
 ---       module = "passes.static_analysis",
 ---       kind   = "diagnostic",
 ---       deps   = {"word-counts", "components"},
----       out    = { { kind = "report", path_template = "<out_root>/<basename>.static_analysis.txt" } }
 ---     }
---- `kind = "diagnostic"` keeps every finding visible in the report; the orchestrator does not exit non-zero on static-analysis errors.
+--- `kind = "diagnostic"` keeps every finding visible in the projection; the orchestrator does not exit non-zero on static-analysis errors.
 --- Annotation and header-output validation remain build-stopping.
----
---- **Conventions**: tabs (1/level), EmmyLua annotations, no regex, Lua 5.3 compatible.
 
 -- ════════════════════════════════════════════════════════════════════════════
 -- Module-scope requires + package.path setup
@@ -148,6 +150,38 @@ local OUTPUT_EXTENSION = ".static_analysis.txt"
 --- @field findings   Finding[] -- findings for this atom
 --- @field total_cycles integer -- sum of token cycle costs
 
+-- ════════════════════════════════════════════════════════════════════════════
+-- Per-word-event helpers
+-- ════════════════════════════════════════════════════════════════════════════
+
+-- Pick the source-line field that best represents "where in the user's source file is this word?".
+--
+-- `word_events` (populated by `passes/emission_model.lua::stamp_root_provenance`) carry four line fields:
+--   * `call_line`  — physical line in the ROOT atom's source (the line of the `mac_X(...)` call site that triggered this emission, or `body_line` for direct words in the atom body)
+--   * `body_line`  — physical line in the body containing the emitted word (the atom body for direct words; the component body for words expanded inside `mac_X(...)`)
+--   * `def_line`   — line of the COMPONENT's declaration in its source file (only meaningful for words emitted inside a component expansion)
+--   * `line`       — body-relative line in the source text (not a physical source line; rarely useful in rendered findings)
+--
+-- For component-expanded words (e.g. the BD-slot nop of `jump_reg(R_AtomJmp)` inside `mac_yield()`),
+-- `body_line` points into the COMPONENT's source file (e.g. `lottes_tape.h:110` for `ac_yield`'s body).
+-- The user editing their atom body expects the line to point at THEIR source — i.e. the line where `mac_yield()`
+-- was called (e.g. `hello_gte_tape.c:35`). That line is `call_line`.
+--
+-- For direct words in the atom body (no invocation wrapping them), `call_line == body_line` already,
+-- so `call_line` works for both cases.
+local function line_for_word_event(ev)
+    if ev == nil then return 0 end
+    return ev.call_line or ev.body_line or ev.line or ev.def_line or 0
+end
+
+-- True iff the given atom/component declaration has the bare `atom_dbg_skip` marker.
+-- Used by the structural handshake checks (`mac_yield_uniformity`, `hazard_nop_use`,
+-- `control_transfer_delay_slot_use`) to exempt runtime-helper declarations (`tape_exit`, `ac_yield`,
+-- and the `ac_*` macro components) from findings whose contract they intentionally don't satisfy.
+local function is_runtime_helper(atom)
+    return atom and atom.debug_skip == true
+end
+
 -- ════════════════════════════════════════════════════════════════════════════
 -- classify_tokens — per-token classification
 -- ════════════════════════════════════════════════════════════════════════════
@@ -551,11 +585,12 @@ local function append_cu2_finding(atom, event, forward, transition,
 	local event_ident = event.encoder or event.ident or "?"
 	local policy      = duffle.CU2_TRANSITION_POLICY or {}
 	local evidence    = policy.evidence or {}
+	local event_line  = line_for_word_event(event)
 	atom.paths.hazards[#atom.paths.hazards + 1] = {
 		check                = "transfer_hazards",
 		kind                 = kind,
 		atom                 = atom.name,
-		line                 = event.body_line or event.line or event.def_line or 0,
+		line                 = event_line,
 		source               = event.def_path or event.source or "",
 		relation_id          = "mtc0_cu2_visibility",
 		semantic             = "MTC0",
@@ -619,10 +654,11 @@ local function consume_cu2_transition(atom, event, ev_word, forward)
 
 	local gap = ev_word - transition.producer_word - 1
 	local target = transition.target_state
+	local event_line = line_for_word_event(event)
 	if target == "unknown" then
 		append_cu2_finding(atom, event, forward, transition, gap, "info", "unknown",
 			string.format("%s at line %d uses COP2 after an MTC0 Status write whose CU2 value is unknown (gap=%d, configured boundary=%d)"
-				, atom.name, event.body_line or event.line or event.def_line or 0
+				, atom.name, event_line
 				, gap, transition.required
 			)
 		)
@@ -635,7 +671,7 @@ local function consume_cu2_transition(atom, event, ev_word, forward)
 		local verb = target == "enabled" and "enable" or "disable"
 		append_cu2_finding(atom, event, forward, transition, gap, "warning", "conservative",
 			string.format("%s at line %d uses COP2 before the SR.CU2 %s transition has settled (gap=%d, required=%d; timing is conservative)"
-				, atom.name, event.body_line or event.line or event.def_line or 0
+				, atom.name, event_line
 				, verb, gap, transition.required
 			)
 		)
@@ -653,7 +689,7 @@ local function consume_cu2_transition(atom, event, ev_word, forward)
 			string.format(
 				"%s at line %d: COP2 unavailable after SR.CU2 was disabled"
 				.. " (gap=%d, required=%d)",
-				atom.name, event.body_line or event.line or event.def_line or 0,
+				atom.name, event_line,
 				gap, transition.required))
 		forward.cu2_state = "disabled"
 	end
@@ -708,7 +744,7 @@ local function analyze_hardware_relations(atom)
 
 	for _, ev in ipairs(events) do
 		local ev_ident  = ev.encoder   or ev.ident  or "?"
-		local ev_line   = ev.body_line or ev.line   or ev.def_line or 0
+		local ev_line   = line_for_word_event(ev)
 		local ev_source = ev.def_path  or ev.source or ""
 		local ev_args   = ev.args      or {}
 		-- `word_events` use `i` as the 0-based word index across the entire expansion.
@@ -867,7 +903,7 @@ local function analyze_hardware_relations(atom)
 
 		-- ── 4. Update semantic role state and stage post-command latch relations. ──
 		-- A GTE command emits outputs with semantic roles (latest_screen_xy, otz, latest_color, etc.) per `duffle.GTE_COMMAND_OUTPUTS`.
-		-- The walker records these on `forward_state.post_command_roles[<register>]` so the `gte_result_position` reader can later detect a reader that picks the wrong register.
+		-- The walker records these on `forward_state.post_command_roles[<register>]` so the `gte_role_mismatch` reader can later detect a reader that picks the wrong register.
 		--
 		-- The walker also stages POST-COMMAND LATCH relations (kind = "command_latch_input"): a subsequent MTC2/CTC2 overwrite of a latched output before the measured boundary is a hazard.
 		-- The relation kind is intentionally separate from the preceding MTC2 → command relation (`MTC2` / `CTC2` / `LWC2`).
@@ -980,7 +1016,7 @@ local function check_gte_input_latch(atom, _pipe_ctx, findings)
 end
 
 -- ─────────────────────────────────────────────────────────────────────────
--- Check #1e: gte_result_position (READER for forward_state semantic roles).
+-- Check #1e: gte_role_mismatch (READER for forward_state semantic roles).
 --
 -- A GTE command emits outputs with semantic roles (latest_screen_xy, otz, latest_color, etc.) per `duffle.GTE_COMMAND_OUTPUTS`.
 -- The forward walker records `forward_state.post_command_roles[<register>]` after each command.
@@ -988,43 +1024,16 @@ end
 -- A subsequent MFC2 (or any encoder that reads a C2 register) that picks the WRONG register for the active role emits a `result_role_mismatch` warning.
 -- For example, reading `C2_SXY0` after RTPS is wrong: the `latest_screen_xy` role is `C2_SXY2`.
 --
+-- Note: the OLD `gte_result_position` check also emitted table-gap info findings for `_post_<cmd>` components missing a row in `duffle.GTE_COMPONENT_RESULT_CONTRACTS`. That table-gap check was based on the `_post_<cmd>` NAMING convention rather than hardware truth, and was removed (the user did not want naming to encode ordering semantics; a proper `atom_info` directive for ordering semantics is a future TODO).
+--
 -- The first `transfer_hazards` reader comment above records the projection contract.
 -- ─────────────────────────────────────────────────────────────────────────
 
-local function check_gte_result_position(atom, _pipe_ctx, findings)
+local function check_gte_role_mismatch(atom, _pipe_ctx, findings)
 	local  forward = atom.paths and atom.paths.forward_state
 	if not forward or not forward.post_command_roles then return end
 	local events = atom.paths.word_events or {}
 
-	-- Build a set of known _post_<cmd> component names whose contract rows we have to verify
-	-- (table-gap detection: a missing row key is itself an info finding).
-	-- The names are the BODY-LEVEL component calls that appear in atom body text;
-	-- The walker doesn't expose body tokens to the reader, so we scan the events' root_call_text.
-	local contracts = duffle.GTE_COMPONENT_RESULT_CONTRACTS or {}
-	local component_names_seen = {}
-	for _, ev in ipairs(events) do
-		local root_call = ev.root_call_text or ev.call_text or ""
-		local name      = root_call:match("^([%w_]+)") or ""
-		if name:find("_post_") then component_names_seen[name] = true end
-	end
-	for component_name in pairs(component_names_seen) do
-		-- Strip any trailing parenthesized argument list / whitespace.
-		local bare = component_name:match("^([%w_]+)") or component_name
-		if contracts[bare] == nil then
-			findings[#findings + 1] = {
-				check          = "gte_result_position",
-				kind           = "info",
-				atom           = atom.name,
-				line           = 0,
-				source         = "",
-				relation_id    = "table_gap",
-				component_name = bare,
-				msg = string.format("%s: component %q has no GTE_COMPONENT_RESULT_CONTRACTS row (unknown _post_<cmd> contract)"
-					, atom.name, bare),
-			}
-		end
-	end
-
 	-- For each word event whose encoder is `gte_mv_from_data_r`, look up the register being read in `forward_state.post_command_roles`.
 	-- If a role is set, the reader's register must match the role's register (the registered "latest_<role>" target).
 	for _, ev in ipairs(events) do
@@ -1047,11 +1056,12 @@ local function check_gte_result_position(atom, _pipe_ctx, findings)
 				-- This is a semantic mismatch.
 				if reg ~= latest_screen_xy_entry.command_register
 					and (reg == "C2_SXY0" or reg == "C2_SXY1") then
+					local ev_line = line_for_word_event(ev)
 					findings[#findings + 1] = {
-						check       = "gte_result_position",
+						check       = "gte_role_mismatch",
 						kind        = "warning",
 						atom        = atom.name,
-						line        = ev.body_line or ev.line or ev.def_line or 0,
+						line        = ev_line,
 						source      = ev.def_path or ev.source or "",
 						relation_id = "result_role_mismatch",
 						semantic    = "result_position",
@@ -1062,7 +1072,7 @@ local function check_gte_result_position(atom, _pipe_ctx, findings)
 						producer_word = latest_screen_xy_entry.producer_word,
 						producer_line = latest_screen_xy_entry.producer_line,
 						msg = string.format("%s at line %d: reading %s after %s but the %s role is C2_SXY2 (not %s)"
-							, atom.name, ev.body_line or ev.line or ev.def_line or 0
+							, atom.name, ev_line
 							, reg, latest_screen_xy_entry.command
 							, latest_screen_xy_entry.role
 							, reg),
@@ -1084,6 +1094,13 @@ end
 -- Branch/jump delay-slot NOPs belong to `control_transfer_delay_slot_use`, so this check leaves them unclassified.
 -- The fixed `mac_yield()` handshake (`jump_reg(R_AtomJmp), nop`) is preserved as suppressed.
 --
+-- Both classifications emit at `info` severity: `modeled-required` documents the model boundary and `modeled-redundant`
+-- is a soft observation ("you have a redundant nop; consider replacing it").
+-- Neither is a logic failure, so neither rises to `warning`.
+--
+-- `atom_dbg_skip` runtime helpers (`tape_exit`, `ac_yield`, the `ac_*` macro components) are exempt:
+-- their structural nops are part of the fixed handshake and not author choices.
+--
 -- The first `transfer_hazards` reader comment above records the projection contract.
 -- ─────────────────────────────────────────────────────────────────────────
 
@@ -1091,6 +1108,9 @@ local function check_hazard_nop_use(atom, _pipe_ctx, findings)
 	local forward = atom.paths and atom.paths.forward_state
 	local events  = atom.paths.word_events or {}
 	if not events or #events == 0 then return end
+	-- Runtime-helper atoms / components (e.g. tape_exit, ac_yield) carry `debug_skip = true` from the bare
+	-- `atom_dbg_skip` marker; their structural nops are part of the fixed handshake and not author choices.
+	if is_runtime_helper(atom) then return end
 
 	-- The walker does not currently snapshot the pending state per event; we replay the same forward walk cheaply here.
 	-- The replay is observation-only (no staging); the only output is one finding per non-BD-slot nop with its classification.
@@ -1100,20 +1120,16 @@ local function check_hazard_nop_use(atom, _pipe_ctx, findings)
 		local ev_ident = ev.encoder or ""
 		local ev_args  = ev.args or {}
 		local ev_word  = ev.i or 0
+		local ev_line  = line_for_word_event(ev)
 
 		-- Classify the nop BEFORE its event is applied to the pending state.
 		if ev_ident == "nop" and prev_ev ~= nil then
 			-- Skip BD-slot nops: they are exclusively owned by control_transfer_delay_slot_use.
+			-- Every BD-slot nop is structural; this check never reports on it.
+			-- (The earlier `if not suppressed then is_bd_slot = true end` form inverted the suppression — the `mac_yield()` handshake's `jump_reg(R_AtomJmp)` was incorrectly flagged.)
 			local prev_ident   = prev_ev.encoder or ""
-			local prev_args   = prev_ev.args or {}
 			local bd_policies  = duffle.CONTROL_TRANSFER_DELAY_SLOT_POLICIES or {}
-			local is_bd_slot  = false
+			local is_bd_slot   = bd_policies[prev_ident] ~= nil
-			local policy      = bd_policies[prev_ident]
-			if policy then
-				local arg1       = prev_args[1]
-				local suppressed = policy.suppress_arg1 and policy.suppress_arg1[arg1] or nil
-				if not suppressed then is_bd_slot = true end
-			end
 			if not is_bd_slot then
 				-- Find a pending modeled relation that this nop would retire.
 				local retired = nil
@@ -1157,7 +1173,7 @@ local function check_hazard_nop_use(atom, _pipe_ctx, findings)
 						check                = "hazard_nop_use",
 						kind                 = "info",
 						atom                 = atom.name,
-						line                 = ev.body_line or ev.line or ev.def_line or 0,
+						line                 = ev_line,
 						source               = ev.def_path or ev.source or "",
 						nop_classification   = "modeled-required",
 						nop_word_index       = ev_word,
@@ -1165,7 +1181,7 @@ local function check_hazard_nop_use(atom, _pipe_ctx, findings)
 						producer_destination = retired.destination,
 						consumer_token       = would_be_consumer or "<would-be-consumer>",
 						msg = string.format("%s at line %d: nop at word %d is modeled-required (retires %s for %s)"
-							, atom.name, ev.body_line or ev.line or ev.def_line or 0, ev_word, retired.relation.id, retired.destination
+							, atom.name, ev_line, ev_word, retired.relation.id, retired.destination
 						),
 					}
 				else
@@ -1173,16 +1189,16 @@ local function check_hazard_nop_use(atom, _pipe_ctx, findings)
 					local slot_kind = "plain"
 					findings[#findings + 1] = {
 						check              = "hazard_nop_use",
-						kind               = "warning",
+						kind               = "info",
 						atom               = atom.name,
-						line               = ev.body_line or ev.line or ev.def_line or 0,
+						line               = ev_line,
 						source             = ev.def_path or ev.source or "",
 						nop_classification = "modeled-redundant",
 						nop_word_index     = ev_word,
 						retired_relation   = nil,
 						slot_kind          = slot_kind,
 						msg = string.format("%s at line %d: nop at word %d is modeled-redundant (no pending modeled relation)"
-							, atom.name, ev.body_line or ev.line or ev.def_line or 0, ev_word
+							, atom.name, ev_line, ev_word
 						),
 					}
 				end
@@ -1254,6 +1270,9 @@ end
 -- Suppress the finding when `policy.suppress_arg1[first_arg]` is non-nil.
 -- The only current suppression is `jump_reg(R_AtomJmp)`, the fixed `mac_yield()` handshake.
 --
+-- `atom_dbg_skip` runtime helpers (`tape_exit`, `ac_yield`, the `ac_*` macro components) are exempt:
+-- their BD slots are part of the fixed handshake (`jump_reg(rret_addr), nop` for tape_exit, `jump_reg(R_AtomJmp), nop` for ac_yield).
+--
 -- `pipe_ctx` is unused; the uniform `(atom, pipe_ctx, findings)` signature is preserved so the check plugs into
 -- the existing CHECK_RULES dispatch without modifying the per-atom loop or analyze_atom_paths.
 -- `passes/emission_model` already normalizes `nop2` to two `nop` events and `atom_label` to zero events, so no special-case branching is needed for either.
@@ -1262,6 +1281,9 @@ end
 local function check_control_transfer_delay_slot_use(atom, pipe_ctx, findings)
 	local  events = atom.paths.word_events or {}
 	if not events or #events == 0 then return end
+	-- Runtime-helper atoms / components (e.g. tape_exit, ac_yield) carry `debug_skip = true` from the bare
+	-- `atom_dbg_skip` marker; their structural BD slots are part of the fixed handshake.
+	if is_runtime_helper(atom) then return end
 	local policies = duffle.CONTROL_TRANSFER_DELAY_SLOT_POLICIES or {}
 	for event_idx, event in ipairs(events) do
 		-- Canonical word_events use `encoder` as the leading identifier of the emitting token).
@@ -1276,9 +1298,9 @@ local function check_control_transfer_delay_slot_use(atom, pipe_ctx, findings)
 				local slot       = events[event_idx + 1]
 				local slot_ident = slot and (slot.encoder or slot.ident) or "<missing>"
 				if slot == nil or (slot.encoder or slot.ident) == "nop" then
-					-- Each word event carries `body_line` as the physical source line.
+					-- Prefer `call_line` (the line of the `mac_X(...)` call site in the atom body) so the rendered
-					-- Use `body_line`, then `def_line`, then 0.
+					-- finding points at the user's source, not at the vendored component body.
-					local ev_line = event.body_line or event.line or event.def_line or 0
+					local ev_line = line_for_word_event(event)
 					findings[#findings + 1] = {
 						atom  = atom.name,
 						line  = ev_line,
@@ -1303,8 +1325,17 @@ end
 --- Empty bodies are not currently flagged — runtime infrastructure atoms like 
 --- `MipsAtom_(yield) { mac_yield() }` and `MipsAtom_(tape_exit) { jump_reg(rret_addr), nop }` 
 --- are valid as-is; mac_yield at the end is the contract.
+---
+--- Runtime helpers carrying the bare `atom_dbg_skip` marker (`tape_exit`, `ac_yield`, the `ac_*` macro components) are exempt:
+--- they intentionally do not follow the standard "1 yield at the end" contract. `tape_exit` performs its own `jump_reg(rret_addr),
+--- nop` to return from the tape runner; `ac_yield` IS the `mac_yield()` implementation.
+--- Flagging them as "missing mac_yield" is signal noise, not a logic failure.
+---
 --- Uses the standard `(atom, pipe_ctx, findings)` signature; `pipe_ctx` is unused.
 local function check_mac_yield_uniformity(atom, pipe_ctx, findings)
+	-- Runtime-helper atoms / components (e.g. tape_exit, ac_yield) carry `debug_skip = true` from the bare
+	-- `atom_dbg_skip` marker; they intentionally break the "1 yield at the end" contract.
+	if is_runtime_helper(atom) then return end
 	-- Per-kind semantics:
 	--   MipsAtom_          (baked atom): exactly 1 mac_yield at the end of the body. Control transfer is the atom's job.
 	--   MipsAtomComp_      (bare static-array component): ZERO mac_yield.
@@ -1935,7 +1966,7 @@ end
 local CHECK_RULES = {
 	{ name = "transfer_hazards",               per_atom   = check_transfer_hazards               },
 	{ name = "gte_input_latch",                per_atom   = check_gte_input_latch                },
-	{ name = "gte_result_position",            per_atom   = check_gte_result_position            },
+	{ name = "gte_role_mismatch",              per_atom   = check_gte_role_mismatch              },
 	{ name = "hazard_nop_use",                 per_atom   = check_hazard_nop_use                 },
 	{ name = "control_transfer_delay_slot_use",per_atom   = check_control_transfer_delay_slot_use},
 	{ name = "mac_yield_uniformity",           per_atom   = check_mac_yield_uniformity           },
@@ -2179,203 +2210,6 @@ local function validate(ctx, src, corpus_pipe_ctx)
 	}
 end
 
--- ════════════════════════════════════════════════════════════════════════════
--- Per-directory output: build/gen/<dir_basename>.static_analysis.txt
--- ════════════════════════════════════════════════════════════════════════════
-
---- Per-directory emit. Aggregates atoms + findings across every source in `dir_sources`
---- and writes a single report to `<out_root>/<dir_basename>.static_analysis.txt`.
---- Called only when at least one atom was found (the caller in M.run handles the skip).
----
---- `info` is finding-level info only (kind == "info" findings); the scanned/cycles summary rows
---- live in `summaries` and are rendered as trailing summary lines after `Module findings:`.
-local function emit_module_static_analysis_txt(ctx, dir, dir_sources, atoms, findings, errors, warnings, info, summaries)
-	-- Module basename = last component of `dir` ("code/duffle" -> "duffle").
-	local dir_basename = dir:match("([^/\\]+)$") or dir
-	local out_path     = ctx.out_root .. "/" .. dir_basename .. ".static_analysis.txt"
-	duffle.ensure_dir(ctx.out_root)
-
-	local lines = {}
-	local function add(s) lines[#lines + 1] = s end
-
-	add("========================================================")
-	add("STATIC ANALYSIS PASS -- module " .. dir_basename)
-	add("========================================================")
-	add(string.format("Sources: %d", #dir_sources))
-	for _, s in ipairs(dir_sources) do
-		add("  " .. s.path)
-	end
-	add("")
-
-	-- Tally atoms by kind for the header summary
-	local n_atoms, n_bare, n_proc = 0, 0, 0
-	for _, a in ipairs(atoms) do
-		n_atoms = n_atoms + 1
-		if     a.kind == "comp_bare" then n_bare = n_bare + 1
-		elseif a.kind == "comp_proc" then n_proc = n_proc + 1
-		end
-	end
-	local header_atoms = string.format("Atoms: %d", n_atoms)
-	if n_bare > 0 or n_proc > 0 then
-		header_atoms = header_atoms .. string.format("  (atoms: %d, comp_bare: %d, comp_proc: %d)",
-			n_atoms - n_bare - n_proc, n_bare, n_proc)
-	end
-	-- Header carries the per-severity counts; info is its own column, not a warning.
-	-- (`Info: N` is the byte-asserted field that the focused test matches; do not collapse it into Warnings.)
-	add(string.format("%s   Findings: %d   Errors: %d   Warnings: %d   Info: %d",
-		header_atoms, #findings, #errors, #warnings, #info))
-	add("")
-
-	-- Group findings by atom (with source prefix when multi-source module)
-	local multi_source = #dir_sources > 1
-	local by_atom      = {}
-	for _, f in ipairs(findings) do
-		by_atom[f.atom] = by_atom[f.atom] or {}
-		by_atom[f.atom][#by_atom[f.atom] + 1] = f
-	end
-
-	if next(by_atom) == nil then
-		add("  (no findings -- every atom passed all checks)")
-	else
-		add("── Findings by atom ─────────────────────────────────────")
-		for _, a in ipairs(atoms) do
-			local fs = by_atom[a.name]
-			if fs then
-				local label = a.name
-				if multi_source and a.source_path then
-					label = string.format("%s  (%s)", a.name, a.source_path:match("([^/\\]+)$") or a.source_path)
-				end
-				add(string.format("  %s   line %d", label, a.line))
-				for _, f in ipairs(fs) do
-					add(string.format("      [%s] %s", f.check, f.msg))
-				end
-			end
-		end
-	end
-
-	add("")
-	add("── Errors ──────────────────────────────────────────────")
-	if #errors == 0 then add("  (none)") end
-	for _, e in ipairs(errors) do
-		add(string.format("  X line %d  %s", e.line, e.msg))
-	end
-
-	add("")
-	add("── Warnings ────────────────────────────────────────────")
-	if #warnings == 0 then add("  (none)") end
-	for _, w in ipairs(warnings) do
-		add(string.format("  ! line %d  %s", w.line, w.msg))
-	end
-
-	-- Finding-level Info section.
-	-- Rendered between Warnings and the per-atom cycle table so the next `── ` line after `── Info` is the per-atom cycle counts section;
-	-- the trailing scan/cycle summary rows (rendered after Module findings) stay outside this section.
-	add("")
-	add("── Info ────────────────────────────────────────────────")
-	if #info == 0 then add("  (none)") end
-	for _, i_ in ipairs(info) do
-		add(string.format("  i line %d  %s", i_.line, i_.msg))
-	end
-
-	-- Per-atom cycle counts (path-aware). For each atom:
-	--   min   = shortest path through the body (earliest exit)
-	--   max   = longest path through the body (full fall-through)
-	--   br    = number of branch instructions
-	--   paths = number of distinct paths reached
-	-- Both min and max are best-case (no stalls); BD-slot nops are absorbed into branch costs (MIPS semantics).
-	add("")
-	add("── Per-atom cycle counts (path-aware, best case, no stalls) ─")
-	if #atoms == 0 then
-		add("  (no atoms)")
-	else
-		-- Sort atoms by max cycles descending for quick scanning.
-		local sorted = {}
-		for _, a in ipairs(atoms) do sorted[#sorted + 1] = a end
-		table.sort(sorted, function(x, y) return ((x.paths or {}).cycles_max or 0) > ((y.paths or {}).cycles_max or 0) end)
-		for _, a in ipairs(sorted) do
-			local p           = a.paths or {}
-			local br_count    = p.branches or 0
-			local path_count  = p.paths or 0
-			local loops_tag   = p.has_loops and "  [loop!]" or ""
-			local unknown_tag = ""
-			if p.unknown_macros and #p.unknown_macros > 0 then
-				unknown_tag = string.format("  [unknown: %s]",
-					table.concat(p.unknown_macros, ", "))
-			end
-			local name_label = a.name
-			if multi_source and a.source_path then
-				name_label = string.format("%s  (%s)", a.name, a.source_path:match("([^/\\]+)$") or a.source_path)
-			end
-			if br_count > 0 then
-				add(string.format("  %-44s  min=%4d  max=%4d  br=%d  paths=%d  (line %d)%s%s",
-					name_label, p.cycles_min or 0, p.cycles_max or 0, br_count, path_count,
-					a.line, loops_tag, unknown_tag))
-			else
-				add(string.format("  %-44s  %4d cycles  (line %d, no branches)%s%s",
-					name_label, p.cycles_min or 0, a.line, loops_tag, unknown_tag))
-			end
-		end
-	end
-
-	add("")
-	add("── Per-source scan summary ──────────────────────────────")
-	-- One line per source that contributed atoms.
-	-- The line includes the source basename + per-source atom count + (if path-aware cycle data is present) the min..max cycle range.
-	-- Sources with 0 atoms are skipped (they're just header files that declared no MipsAtom_ — they're already listed in the module's "Sources:" section above).
-	for _, src in ipairs(dir_sources) do
-		local src_atoms = {}
-		for _, a in ipairs(atoms) do
-			if a.source_path == src.path then
-				src_atoms[#src_atoms + 1] = a
-			end
-		end
-		if #src_atoms == 0 then
-			goto continue
-		end
-		local atom_count = #src_atoms
-		local mn, mx     = math.huge, -1
-		for _, a in ipairs(src_atoms) do
-			local p = a.paths or {}
-			if (p.cycles_min or 0) < mn then mn = p.cycles_min or 0 end
-			if (p.cycles_max or 0) > mx then mx = p.cycles_max or 0 end
-		end
-		local path_str
-		if mx > 0 then
-			path_str = string.format("  cycles=%d..%d", mn, mx)
-		else
-			path_str = string.format("  %d cycles", mn)
-		end
-		add(string.format("  %-30s  %d atom%s%s",
-			src.basename, atom_count,
-			atom_count == 1 and "" or "s",
-			path_str))
-		::continue::
-	end
-
-	-- Module-level findings summary (across all sources).
-	-- Info has its own count; it remains separate from warnings.
-	local total_errs  = #errors
-	local total_warns = #warnings
-	local total_infos = #info
-	add("")
-	add(string.format("Module findings:  %d error(s), %d warning(s), %d info", total_errs, total_warns, total_infos))
-
-	-- Per-source "scanned:" / "cycles:" summary lines (each line includes the source basename for traceability).
-	-- These are kept SEPARATE from the finding-level Info section above so the report's Info section is signal-only
-	-- (true findings), not a mix of findings + rollups.
-	-- The downstream test (`test_control_transfer_delay_slot.lua`)
-	-- asserts that the Info section contains NEITHER `scanned:` NOR `cycles:` lines.
-	if summaries and #summaries > 0 then
-		add("")
-		for _, s in ipairs(summaries) do
-			add(string.format("  %s", s.msg))
-		end
-	end
-
-	duffle.write_file(out_path, table.concat(lines, "\n") .. "\n")
-	return out_path
-end
-
 -- ════════════════════════════════════════════════════════════════════════════
 -- M.run — orchestrator entry
 -- ════════════════════════════════════════════════════════════════════════════
@@ -2431,21 +2265,30 @@ function M.run(ctx)
 			for _, s  in ipairs(result.summaries or {}) do dir_summaries[#dir_summaries + 1] = s end
 		end
 
-		-- Skip directories with zero atoms. A directory with only headers / no MipsAtom_ is "nothing to report".
+		-- Stash per-module results on the corpus for `report.lua` to consume.
-		if #all_atoms == 0 then
+		-- Avoids re-running validate() in the report pass + avoids rebuilding corpus_pipe_ctx.
-			-- Still aggregate errors/warnings/info so orchestrator sees them, but don't write a file.
+		-- Pattern matches `corpus.atoms_by_name` / `corpus.word_counts` / `corpus.components`
+		-- (one writer: `static_analysis.lua`; one reader: `report.lua`).
+		-- Module basename = last component of `dir` ("code/duffle" -> "duffle").
+		local dir_basename = dir:match("([^/\\]+)$") or dir
+		corpus.static_analysis_results = corpus.static_analysis_results or {}
+		corpus.static_analysis_results[dir_basename] = {
+			atoms     = all_atoms,
+			findings  = all_findings,
+			errors    = dir_errors,
+			warnings  = dir_warnings,
+			info      = dir_info,
+			summaries = dir_summaries,
+			sources   = dir_sources,
+		}
+
+		-- Aggregate per-dir errors/warnings/info into the orchestrator totals.
+		-- Hoisted out of any per-dir file-emit so `report.lua` can drop the on-disk file emitter without losing the cross-module rollup.
 		for _, e in ipairs(dir_errors)   do errors  [#errors   + 1] = e end
 		for _, w in ipairs(dir_warnings) do warnings[#warnings + 1] = w end
 		for _, i_ in ipairs(dir_info)     do info    [#info     + 1] = i_ end
-		else
+		-- (No per-dir emit: per-module findings are stashed on `corpus.static_analysis_results` above. 
-			local out_path = emit_module_static_analysis_txt(ctx, dir, dir_sources, all_atoms, all_findings, dir_errors, dir_warnings, dir_info, dir_summaries)
+		-- `report.lua` reads that projection to render `<module>.atom_meta_report.md` without re-running validate().)
-			if out_path then
-				table.insert(outputs, { static_analysis_txt = out_path })
-			end
-			for _, e in ipairs(dir_errors) do errors  [#errors   + 1] = e end
-			for _, w in ipairs(dir_warnings) do warnings[#warnings + 1] = w end
-			for _, i_ in ipairs(dir_info) do info[#info + 1] = i_ end
-		end
 	end
 
 	-- Result exposes at least {outputs, errors, warnings, info}.

scripts/ps1_meta.lua

@@ -2,17 +2,14 @@
 ---
 --- Dispatches to pass modules under `scripts/passes/`, resolving dependencies topologically (Kahn's algorithm + cycle detection).
 ---
---- **Architecture**:
+--- Architecture:
----   - **PASSES table** — declarative dep graph (data, not code).
+---   - PASSES table: Declarative dep graph (data, not code).
----   - **FLAG_HANDLERS table** — maps CLI flags to handlers.
+---   - FLAG_HANDLERS table: Maps CLI flags to handlers.
----   - **parse_args** → **build_ctx** (resolves unity/direct includes or exact sources; no semantic scanning) → **topo_sort** → **dispatch_passes**.
+---   - parse_args → build_ctx (resolves unity/direct includes or exact sources) → topo_sort → dispatch_passes.
 ---   - The first pass in the dep graph is `scan-source` (see `passes/scan_source.lua`).
 ---     It calls `duffle.scan_source` once per source to produce the fat `SourceScan` payload, which is attached to each `src.scan`. 
 ---     Every other pass that reads source structure depends on `scan-source` and consumes `src.scan` as a read-only. 
 ---
---- **Conventions**: tabs (1/level), EmmyLua annotations, no regex,
---- Lua 5.3 compatible.
----
 -- ════════════════════════════════════════════════════════════════════════════
 -- Module-scope requires + package.path setup
 -- ════════════════════════════════════════════════════════════════════════════
@@ -160,7 +157,7 @@ local PASSES = {
 	report = {
 		module = "passes.report",
 		kind   = "report",
-		deps   = {"annotation", "static-analysis"},
+		deps   = {"annotation", "static-analysis", "atoms-source-map"},  -- +atoms-source-map (consolidated-report-files refactor, 2026-07-26)
 		groups = { "pre-link" },
 	},
 }
@@ -206,7 +203,8 @@ end
 
 -- Pass-kind taxonomy: Which kinds stop the build on errors?
 --
--- Report severity is independent from process exit policy. A "diagnostic" pass still writes every `error`/`warning` finding into its report file,
+-- Report severity is independent from process exit policy.
+-- A "diagnostic" pass still writes every `error`/`warning` finding into its report file,
 -- but `report_validation_errors` returns early for non-stopping kinds, so nothing is printed to stderr and the orchestrator does not exit non-zero.
 -- Adding a new pass kind requires listing it here explicitly; an unknown kind must not silently fall back to "true".
 local PASS_KIND_STOP_ON_ERROR = {