A maze feels kinder when a turn pressed just before a junction happens as soon as the route opens.
Use it in a project
CELL indexes a 4×4 row-major map; zero cells are walkable and nonzero cells block. Directions are 0 still, 1 left, 2 right, 3 up, 4 down. A nonzero REQUEST replaces PENDING. Try that turn first; if blocked, retain it and try the current DIRECTION. A successful turn clears PENDING. Each call moves at most one cell. Invalid indices/directions or a blocked current cell return VALID=0 without changing movement state.
Include component.inc once (MOS callers include the shared 6502 implementation through it). Reserve the public fields in this exact order: CELL, DIRECTION, PENDING, MOVED, VALID, REQUEST, C0, C1, C2, C3, C4, C5, C6, C7, C8, C9, C10, C11, C12, C13, C14, C15. They occupy 22 contiguous bytes. Also reserve the private workspace: T0, T1, T2, T3, T4 (5 bytes). Array names in the explanation refer to the numbered consecutive bindings, such as C0, C1 and so on.
Call grid_turn_buffer_init once at the intended reset boundary. It clears inputs as well as outputs and workspace. Set your starting state and configuration afterwards, then call grid_turn_buffer_step whenever the described event occurs. The helper reads no device, waits for no frame and installs no interrupt handler.
| Ownership | Fields |
|---|---|
| Retain between calls | CELL, DIRECTION and PENDING; map bytes |
| Supply before service | REQUEST |
| Read after service | CELL, DIRECTION, PENDING, MOVED and VALID |
Try at most two neighbouring cells: the buffered request and the existing direction. Check column boundaries before adding or subtracting one so movement cannot wrap into the next row.
Reusable initialisation and service
; SPDX-License-Identifier: MIT
; Buffer Turns Through a Grid. See README.md for the byte interface and ownership.
; init clears the public fields and private workspace; set inputs afterwards.
grid_turn_buffer_init:
ld a,0
ld (CELL),a
ld (DIRECTION),a
ld (PENDING),a
ld (MOVED),a
ld (VALID),a
ld (REQUEST),a
ld (C0),a
ld (C1),a
ld (C2),a
ld (C3),a
ld (C4),a
ld (C5),a
ld (C6),a
ld (C7),a
ld (C8),a
ld (C9),a
ld (C10),a
ld (C11),a
ld (C12),a
ld (C13),a
ld (C14),a
ld (C15),a
ld (T0),a
ld (T1),a
ld (T2),a
ld (T3),a
ld (T4),a
ret
grid_turn_buffer_step:
; MOVED = 0
ld a,0
ld (MOVED),a
; VALID = 0
ld a,0
ld (VALID),a
; if CELL >= 16:
ld a,(CELL)
cp 16
jp nc,grid_turn_buffer_L1
jp grid_turn_buffer_L2
grid_turn_buffer_L1:
; return
ret
jp grid_turn_buffer_L3
grid_turn_buffer_L2:
grid_turn_buffer_L3:
; if DIRECTION > 4:
ld a,(DIRECTION)
cp 4
jp z,grid_turn_buffer_L5
jp nc,grid_turn_buffer_L4
jp grid_turn_buffer_L5
grid_turn_buffer_L4:
; return
ret
jp grid_turn_buffer_L6
grid_turn_buffer_L5:
grid_turn_buffer_L6:
; if PENDING > 4:
ld a,(PENDING)
cp 4
jp z,grid_turn_buffer_L8
jp nc,grid_turn_buffer_L7
jp grid_turn_buffer_L8
grid_turn_buffer_L7:
; return
ret
jp grid_turn_buffer_L9
grid_turn_buffer_L8:
grid_turn_buffer_L9:
; if REQUEST > 4:
ld a,(REQUEST)
cp 4
jp z,grid_turn_buffer_L11
jp nc,grid_turn_buffer_L10
jp grid_turn_buffer_L11
grid_turn_buffer_L10:
; return
ret
jp grid_turn_buffer_L12
grid_turn_buffer_L11:
grid_turn_buffer_L12:
; T0 = C[CELL]
ld a,(CELL)
ld e,a
ld d,0
ld hl,C0
add hl,de
ld a,(hl)
ld (T0),a
; if T0 != 0:
ld a,(T0)
cp 0
jp nz,grid_turn_buffer_L13
jp grid_turn_buffer_L14
grid_turn_buffer_L13:
; return
ret
jp grid_turn_buffer_L15
grid_turn_buffer_L14:
grid_turn_buffer_L15:
; VALID = 1
ld a,1
ld (VALID),a
; if REQUEST != 0:
ld a,(REQUEST)
cp 0
jp nz,grid_turn_buffer_L16
jp grid_turn_buffer_L17
grid_turn_buffer_L16:
; PENDING = REQUEST
ld a,(REQUEST)
ld (PENDING),a
jp grid_turn_buffer_L18
grid_turn_buffer_L17:
grid_turn_buffer_L18:
; T4 = 2
ld a,2
ld (T4),a
; T0 = PENDING
ld a,(PENDING)
ld (T0),a
; while T4 != 0:
grid_turn_buffer_L19:
ld a,(T4)
cp 0
jp nz,grid_turn_buffer_L20
jp grid_turn_buffer_L21
grid_turn_buffer_L20:
; T1 = 255
ld a,255
ld (T1),a
; T2 = CELL & 3
ld a,(CELL)
and 3
ld (T2),a
; if T0 == 1:
ld a,(T0)
cp 1
jp z,grid_turn_buffer_L22
jp grid_turn_buffer_L23
grid_turn_buffer_L22:
; if T2 != 0:
ld a,(T2)
cp 0
jp nz,grid_turn_buffer_L25
jp grid_turn_buffer_L26
grid_turn_buffer_L25:
; T1 = CELL - 1
ld a,(CELL)
sub 1
ld (T1),a
jp grid_turn_buffer_L27
grid_turn_buffer_L26:
grid_turn_buffer_L27:
jp grid_turn_buffer_L24
grid_turn_buffer_L23:
grid_turn_buffer_L24:
; if T0 == 2:
ld a,(T0)
cp 2
jp z,grid_turn_buffer_L28
jp grid_turn_buffer_L29
grid_turn_buffer_L28:
; if T2 != 3:
ld a,(T2)
cp 3
jp nz,grid_turn_buffer_L31
jp grid_turn_buffer_L32
grid_turn_buffer_L31:
; T1 = CELL + 1
ld a,(CELL)
add a,1
ld (T1),a
jp grid_turn_buffer_L33
grid_turn_buffer_L32:
grid_turn_buffer_L33:
jp grid_turn_buffer_L30
grid_turn_buffer_L29:
grid_turn_buffer_L30:
; if T0 == 3:
ld a,(T0)
cp 3
jp z,grid_turn_buffer_L34
jp grid_turn_buffer_L35
grid_turn_buffer_L34:
; if CELL >= 4:
ld a,(CELL)
cp 4
jp nc,grid_turn_buffer_L37
jp grid_turn_buffer_L38
grid_turn_buffer_L37:
; T1 = CELL - 4
ld a,(CELL)
sub 4
ld (T1),a
jp grid_turn_buffer_L39
grid_turn_buffer_L38:
grid_turn_buffer_L39:
jp grid_turn_buffer_L36
grid_turn_buffer_L35:
grid_turn_buffer_L36:
; if T0 == 4:
ld a,(T0)
cp 4
jp z,grid_turn_buffer_L40
jp grid_turn_buffer_L41
grid_turn_buffer_L40:
; if CELL < 12:
ld a,(CELL)
cp 12
jp c,grid_turn_buffer_L43
jp grid_turn_buffer_L44
grid_turn_buffer_L43:
; T1 = CELL + 4
ld a,(CELL)
add a,4
ld (T1),a
jp grid_turn_buffer_L45
grid_turn_buffer_L44:
grid_turn_buffer_L45:
jp grid_turn_buffer_L42
grid_turn_buffer_L41:
grid_turn_buffer_L42:
; if T1 < 16:
ld a,(T1)
cp 16
jp c,grid_turn_buffer_L46
jp grid_turn_buffer_L47
grid_turn_buffer_L46:
; T3 = C[T1]
ld a,(T1)
ld e,a
ld d,0
ld hl,C0
add hl,de
ld a,(hl)
ld (T3),a
; if T3 == 0:
ld a,(T3)
cp 0
jp z,grid_turn_buffer_L49
jp grid_turn_buffer_L50
grid_turn_buffer_L49:
; CELL = T1
ld a,(T1)
ld (CELL),a
; DIRECTION = T0
ld a,(T0)
ld (DIRECTION),a
; if T4 == 2:
ld a,(T4)
cp 2
jp z,grid_turn_buffer_L52
jp grid_turn_buffer_L53
grid_turn_buffer_L52:
; PENDING = 0
ld a,0
ld (PENDING),a
jp grid_turn_buffer_L54
grid_turn_buffer_L53:
grid_turn_buffer_L54:
; MOVED = 1
ld a,1
ld (MOVED),a
; return
ret
jp grid_turn_buffer_L51
grid_turn_buffer_L50:
grid_turn_buffer_L51:
jp grid_turn_buffer_L48
grid_turn_buffer_L47:
grid_turn_buffer_L48:
; T4 = T4 - 1
ld a,(T4)
sub 1
ld (T4),a
; T0 = DIRECTION
ld a,(DIRECTION)
ld (T0),a
jp grid_turn_buffer_L19
grid_turn_buffer_L21:
ret
component_end:Machine contract
AF/BC/DE/HL may change; IX/IY are preserved. A direct CALL needs two return-address stack bytes. The helper makes no nested calls and adds no other stack use. Its named scratch is private workspace, not a pointer, a ROM variable or shared zero-page space that the game may borrow concurrently. The samples use fixed symbol bindings. Scope or rename every label and binding, including the component_end measurement marker, and allocate a separate block for each independent instance. Different helpers can also use common field names, so combining them needs separate namespaces or explicitly renamed bindings. Give each block one mutation owner.
The 48K diagnostic boots through ROM tape loading and USR, disables interrupts and owns the screen. The helper performs no port or screen writes.
Adapt the caller
demo.asm supplies the bindings and include order. exercise.inc first runs table cases, then a separate client retaining state between calls. A game can call the public step entry directly and remove the diagnostic packet and display. Do not copy the diagnostic’s hardware takeover into an existing game loop.
Build with make ASM198X=/path/to/asm198x. The Makefile produces normal, custom, deliberately wrong and repaired programs. Tools must already be installed; the sample downloads nothing.
Bindings and include order
org $8000
CUSTOM equ 0
BROKEN equ 0
COYOTE_STEPS equ 4
BUFFER_STEPS equ 4
TEXT_CAP equ 8
PROPERTY_COUNT equ 16
STREAM_BYTES equ 13
CRC_POLY equ 7
include "caller.inc"
include "exercise.inc"
component_start:
include "component.inc"
include "data.inc"
include "cases.inc"
include "../../physics/rectangle-overlap/display.inc"
code_end:
STATE:
CELL: defb 0
DIRECTION: defb 0
PENDING: defb 0
MOVED: defb 0
VALID: defb 0
REQUEST: defb 0
C0: defb 0
C1: defb 0
C2: defb 0
C3: defb 0
C4: defb 0
C5: defb 0
C6: defb 0
C7: defb 0
C8: defb 0
C9: defb 0
C10: defb 0
C11: defb 0
C12: defb 0
C13: defb 0
C14: defb 0
C15: defb 0
T0: defb 0
T1: defb 0
T2: defb 0
T3: defb 0
T4: defb 0
input_ptr: defw 0
output_ptr: defw 0
cases_left: defb 0
ready: defb 0
preview: defs 8,0
OUTPUT: defs 1300,0
end startA client retaining state between calls
preview_rules:
if CUSTOM
; CELL = 0
ld a,0
ld (CELL),a
; DIRECTION = 2
ld a,2
ld (DIRECTION),a
; REQUEST = 3
ld a,3
ld (REQUEST),a
if BROKEN
; PENDING = 0
ld a,0
ld (PENDING),a
endif
call checked_step
call emit_state
; REQUEST = 0
ld a,0
ld (REQUEST),a
if BROKEN
; PENDING = 0
ld a,0
ld (PENDING),a
endif
call checked_step
call emit_state
; REQUEST = 4
ld a,4
ld (REQUEST),a
if BROKEN
; PENDING = 0
ld a,0
ld (PENDING),a
endif
call checked_step
call emit_state
ret
else
; CELL = 8
ld a,8
ld (CELL),a
; DIRECTION = 2
ld a,2
ld (DIRECTION),a
; REQUEST = 3
ld a,3
ld (REQUEST),a
; C4 = 1
ld a,1
ld (C4),a
if BROKEN
; PENDING = 0
ld a,0
ld (PENDING),a
endif
call checked_step
call emit_state
; REQUEST = 0
ld a,0
ld (REQUEST),a
if BROKEN
; PENDING = 0
ld a,0
ld (PENDING),a
endif
call checked_step
call emit_state
if BROKEN
; PENDING = 0
ld a,0
ld (PENDING),a
endif
call checked_step
call emit_state
endif
retCustomise it
Queue a blocked upward turn at the top edge, then replace it with a downward request. The maintained custom caller changes its inputs or client sequence rather than hiding a different implementation behind the same label. Compare every state of the two clients, not only their final display.
Custom client selection
org $8000
CUSTOM equ 1
BROKEN equ 0
COYOTE_STEPS equ 2
BUFFER_STEPS equ 2
TEXT_CAP equ 4
PROPERTY_COUNT equ 16
STREAM_BYTES equ 13
CRC_POLY equ 49
include "caller.inc"
include "exercise.inc"
component_start:
include "component.inc"
include "data.inc"
include "cases.inc"
include "../../physics/rectangle-overlap/display.inc"
code_end:
STATE:
CELL: defb 0
DIRECTION: defb 0
PENDING: defb 0
MOVED: defb 0
VALID: defb 0
REQUEST: defb 0
C0: defb 0
C1: defb 0
C2: defb 0
C3: defb 0
C4: defb 0
C5: defb 0
C6: defb 0
C7: defb 0
C8: defb 0
C9: defb 0
C10: defb 0
C11: defb 0
C12: defb 0
C13: defb 0
C14: defb 0
C15: defb 0
T0: defb 0
T1: defb 0
T2: defb 0
T3: defb 0
T4: defb 0
input_ptr: defw 0
output_ptr: defw 0
cases_left: defb 0
ready: defb 0
preview: defs 8,0
OUTPUT: defs 1300,0
end startThe custom diagnostic row is 06 04 00 01 01 04 00 00. The full client trace in the source explains how it gets there.
Mistake and repair
The wrong caller clears the queued turn between cells. The player continues along the row instead of turning upwards when the next junction opens. Retain PENDING until a turn succeeds or a new request replaces it.
The BROKEN branch lives in the sequential client, not the reusable helper. wrong.asm selects it; repaired.asm restores the normal call sequence. The repaired executable matches the normal program (for Spectrum, compare loaded CODE rather than the tape filename).
Select the deliberately wrong client
org $8000
CUSTOM equ 0
BROKEN equ 1
COYOTE_STEPS equ 4
BUFFER_STEPS equ 4
TEXT_CAP equ 8
PROPERTY_COUNT equ 16
STREAM_BYTES equ 13
CRC_POLY equ 7
include "caller.inc"
include "exercise.inc"
component_start:
include "component.inc"
include "data.inc"
include "cases.inc"
include "../../physics/rectangle-overlap/display.inc"
code_end:
STATE:
CELL: defb 0
DIRECTION: defb 0
PENDING: defb 0
MOVED: defb 0
VALID: defb 0
REQUEST: defb 0
C0: defb 0
C1: defb 0
C2: defb 0
C3: defb 0
C4: defb 0
C5: defb 0
C6: defb 0
C7: defb 0
C8: defb 0
C9: defb 0
C10: defb 0
C11: defb 0
C12: defb 0
C13: defb 0
C14: defb 0
C15: defb 0
T0: defb 0
T1: defb 0
T2: defb 0
T3: defb 0
T4: defb 0
input_ptr: defw 0
output_ptr: defw 0
cases_left: defb 0
ready: defb 0
preview: defs 8,0
OUTPUT: defs 1300,0
end start
Cost and alternatives
The measured helper extent is 493 code bytes; public state is 22 bytes and private scratch is 5 bytes. There are no immutable helper tables. Caller data, the test cases, return-address stack, alignment and display buffers cost additional space. These are assembled sizes, not cycle measurements.
At most two map reads after validation. A larger map needs a wider index and declared dimensions; a pixel mover needs centre-line snapping and collision checks between cell boundaries.
This is logical cell movement, not pixel interpolation or a complete maze controller. Call only at a cell-step boundary; animate between those positions separately. The map is read-only during service.
Execution evidence
Four variants run on 48K PAL ROM tape load and USR, using Asm198x 0.0.72, Emu198x 0.44.2. Each executes 45 boundary/varied/error table cases, dirty initialisation and the separate retained-state client. An independent mathematical/container model checks every public byte after every call. This is bounded example coverage, not exhaustive correctness for every possible state.
The records retain loaded immutable code, completion, register sentinels, full packets, source/tool/firmware hashes and captures. The public gate validates these retained observations and rejects altered evidence; it does not run restricted firmware. No firmware is distributed. The eight displayed bytes are the first eight public fields, zero-padded when shorter; the packet includes every field.
Where it fits
Four-way input: Resolve contradictory buttons before turning the result into a buffered movement request.