Merge loops/forth into architecture: Hayes conformance 99% (632/638), JIT cooperation, full Forth-2012 core

2026-05-13 20:37:26 +00:00
parent 129f11fdbc aad178aa0f
commit c19bcc51cb
16 changed files with 5916 additions and 207 deletions
--- a/lib/forth/ans-tests/README.md
+++ b/lib/forth/ans-tests/README.md
@@ -0,0 +1,14 @@
+ANS Forth conformance tests — vendored from
+https://github.com/gerryjackson/forth2012-test-suite (master, commit-locked
+on first fetch: 2026-04-24).
+
+Files in this directory are pristine copies of upstream — do not edit them.
+They are consumed by the conformance runner in `lib/forth/conformance.sh`.
+
+- `tester.fr` — John Hayes' test harness (`T{ ... -> ... }T`). (C) 1995
+  Johns Hopkins APL, distributable under its notice.
+- `core.fr` — Core word set tests (Hayes, ~1000 lines).
+- `coreexttest.fth` — Core Extension tests (Gerry Jackson).
+
+Only `core.fr` is expected to run green end-to-end for Phase 3; the others
+stay parked until later phases.
--- a/lib/forth/ans-tests/core.fr
+++ b/lib/forth/ans-tests/core.fr
--- a/lib/forth/ans-tests/coreexttest.fth
+++ b/lib/forth/ans-tests/coreexttest.fth
@@ -0,0 +1,775 @@
+\ To test the ANS Forth Core Extension word set
+
+\ This program was written by Gerry Jackson in 2006, with contributions from
+\ others where indicated, and is in the public domain - it can be distributed
+\ and/or modified in any way but please retain this notice.
+
+\ This program is distributed in the hope that it will be useful,
+\ but WITHOUT ANY WARRANTY; without even the implied warranty of
+\ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+
+\ The tests are not claimed to be comprehensive or correct 
+
+\ ------------------------------------------------------------------------------
+\ Version 0.15 1 August 2025 Added two tests to VALUE
+\         0.14 21 July 2022 Updated first line of BUFFER: test as recommended
+\              in issue 32
+\         0.13 28 October 2015
+\              Replace <FALSE> and <TRUE> with FALSE and TRUE to avoid
+\              dependence on Core tests
+\              Moved SAVE-INPUT and RESTORE-INPUT tests in a file to filetest.fth
+\              Use of 2VARIABLE (from optional wordset) replaced with CREATE.
+\              Minor lower to upper case conversions.
+\              Calls to COMPARE replaced by S= (in utilities.fth) to avoid use
+\              of a word from an optional word set.
+\              UNUSED tests revised as UNUSED UNUSED = may return FALSE when an
+\              implementation has the data stack sharing unused dataspace.
+\              Double number input dependency removed from the HOLDS tests.
+\              Minor case sensitivities removed in definition names.
+\         0.11 25 April 2015
+\              Added tests for PARSE-NAME HOLDS BUFFER:
+\              S\" tests added
+\              DEFER IS ACTION-OF DEFER! DEFER@ tests added
+\              Empty CASE statement test added
+\              [COMPILE] tests removed because it is obsolescent in Forth 2012
+\         0.10 1 August 2014
+\             Added tests contributed by James Bowman for:
+\                <> U> 0<> 0> NIP TUCK ROLL PICK 2>R 2R@ 2R>
+\                HEX WITHIN UNUSED AGAIN MARKER
+\             Added tests for:
+\                .R U.R ERASE PAD REFILL SOURCE-ID 
+\             Removed ABORT from NeverExecuted to enable Win32
+\             to continue after failure of RESTORE-INPUT.
+\             Removed max-intx which is no longer used.
+\         0.7 6 June 2012 Extra CASE test added
+\         0.6 1 April 2012 Tests placed in the public domain.
+\             SAVE-INPUT & RESTORE-INPUT tests, position
+\             of T{ moved so that tests work with ttester.fs
+\             CONVERT test deleted - obsolete word removed from Forth 200X
+\             IMMEDIATE VALUEs tested
+\             RECURSE with :NONAME tested
+\             PARSE and .( tested
+\             Parsing behaviour of C" added
+\         0.5 14 September 2011 Removed the double [ELSE] from the
+\             initial SAVE-INPUT & RESTORE-INPUT test
+\         0.4 30 November 2009  max-int replaced with max-intx to
+\             avoid redefinition warnings.
+\         0.3  6 March 2009 { and } replaced with T{ and }T
+\                           CONVERT test now independent of cell size
+\         0.2  20 April 2007 ANS Forth words changed to upper case
+\                            Tests qd3 to qd6 by Reinhold Straub
+\         0.1  Oct 2006 First version released
+\ -----------------------------------------------------------------------------
+\ The tests are based on John Hayes test program for the core word set
+
+\ Words tested in this file are:
+\     .( .R 0<> 0> 2>R 2R> 2R@ :NONAME <> ?DO AGAIN C" CASE COMPILE, ENDCASE
+\     ENDOF ERASE FALSE HEX MARKER NIP OF PAD PARSE PICK REFILL
+\     RESTORE-INPUT ROLL SAVE-INPUT SOURCE-ID TO TRUE TUCK U.R U> UNUSED
+\     VALUE WITHIN [COMPILE]
+
+\ Words not tested or partially tested:
+\     \ because it has been extensively used already and is, hence, unnecessary
+\     REFILL and SOURCE-ID from the user input device which are not possible
+\     when testing from a file such as this one
+\     UNUSED (partially tested) as the value returned is system dependent
+\     Obsolescent words #TIB CONVERT EXPECT QUERY SPAN TIB as they have been
+\     removed from the Forth 2012 standard
+
+\ Results from words that output to the user output device have to visually
+\ checked for correctness. These are .R U.R .(
+
+\ -----------------------------------------------------------------------------
+\ Assumptions & dependencies:
+\     - tester.fr (or ttester.fs), errorreport.fth and utilities.fth have been
+\       included prior to this file
+\     - the Core word set available
+\ -----------------------------------------------------------------------------
+TESTING Core Extension words
+
+DECIMAL
+
+TESTING TRUE FALSE
+
+T{ TRUE  -> 0 INVERT }T
+T{ FALSE -> 0 }T
+
+\ -----------------------------------------------------------------------------
+TESTING <> U>   (contributed by James Bowman)
+
+T{ 0 0 <> -> FALSE }T
+T{ 1 1 <> -> FALSE }T
+T{ -1 -1 <> -> FALSE }T
+T{ 1 0 <> -> TRUE }T
+T{ -1 0 <> -> TRUE }T
+T{ 0 1 <> -> TRUE }T
+T{ 0 -1 <> -> TRUE }T
+
+T{ 0 1 U> -> FALSE }T
+T{ 1 2 U> -> FALSE }T
+T{ 0 MID-UINT U> -> FALSE }T
+T{ 0 MAX-UINT U> -> FALSE }T
+T{ MID-UINT MAX-UINT U> -> FALSE }T
+T{ 0 0 U> -> FALSE }T
+T{ 1 1 U> -> FALSE }T
+T{ 1 0 U> -> TRUE }T
+T{ 2 1 U> -> TRUE }T
+T{ MID-UINT 0 U> -> TRUE }T
+T{ MAX-UINT 0 U> -> TRUE }T
+T{ MAX-UINT MID-UINT U> -> TRUE }T
+
+\ -----------------------------------------------------------------------------
+TESTING 0<> 0>   (contributed by James Bowman)
+
+T{ 0 0<> -> FALSE }T
+T{ 1 0<> -> TRUE }T
+T{ 2 0<> -> TRUE }T
+T{ -1 0<> -> TRUE }T
+T{ MAX-UINT 0<> -> TRUE }T
+T{ MIN-INT 0<> -> TRUE }T
+T{ MAX-INT 0<> -> TRUE }T
+
+T{ 0 0> -> FALSE }T
+T{ -1 0> -> FALSE }T
+T{ MIN-INT 0> -> FALSE }T
+T{ 1 0> -> TRUE }T
+T{ MAX-INT 0> -> TRUE }T
+
+\ -----------------------------------------------------------------------------
+TESTING NIP TUCK ROLL PICK   (contributed by James Bowman)
+
+T{ 1 2 NIP -> 2 }T
+T{ 1 2 3 NIP -> 1 3 }T
+
+T{ 1 2 TUCK -> 2 1 2 }T
+T{ 1 2 3 TUCK -> 1 3 2 3 }T
+
+T{ : RO5 100 200 300 400 500 ; -> }T
+T{ RO5 3 ROLL -> 100 300 400 500 200 }T
+T{ RO5 2 ROLL -> RO5 ROT }T
+T{ RO5 1 ROLL -> RO5 SWAP }T
+T{ RO5 0 ROLL -> RO5 }T
+
+T{ RO5 2 PICK -> 100 200 300 400 500 300 }T
+T{ RO5 1 PICK -> RO5 OVER }T
+T{ RO5 0 PICK -> RO5 DUP }T
+
+\ -----------------------------------------------------------------------------
+TESTING 2>R 2R@ 2R>   (contributed by James Bowman)
+
+T{ : RR0 2>R 100 R> R> ; -> }T
+T{ 300 400 RR0 -> 100 400 300 }T
+T{ 200 300 400 RR0 -> 200 100 400 300 }T
+
+T{ : RR1 2>R 100 2R@ R> R> ; -> }T
+T{ 300 400 RR1 -> 100 300 400 400 300 }T
+T{ 200 300 400 RR1 -> 200 100 300 400 400 300 }T
+
+T{ : RR2 2>R 100 2R> ; -> }T
+T{ 300 400 RR2 -> 100 300 400 }T
+T{ 200 300 400 RR2 -> 200 100 300 400 }T
+
+\ -----------------------------------------------------------------------------
+TESTING HEX   (contributed by James Bowman)
+
+T{ BASE @ HEX BASE @ DECIMAL BASE @ - SWAP BASE ! -> 6 }T
+
+\ -----------------------------------------------------------------------------
+TESTING WITHIN   (contributed by James Bowman)
+
+T{ 0 0 0 WITHIN -> FALSE }T
+T{ 0 0 MID-UINT WITHIN -> TRUE }T
+T{ 0 0 MID-UINT+1 WITHIN -> TRUE }T
+T{ 0 0 MAX-UINT WITHIN -> TRUE }T
+T{ 0 MID-UINT 0 WITHIN -> FALSE }T
+T{ 0 MID-UINT MID-UINT WITHIN -> FALSE }T
+T{ 0 MID-UINT MID-UINT+1 WITHIN -> FALSE }T
+T{ 0 MID-UINT MAX-UINT WITHIN -> FALSE }T
+T{ 0 MID-UINT+1 0 WITHIN -> FALSE }T
+T{ 0 MID-UINT+1 MID-UINT WITHIN -> TRUE }T
+T{ 0 MID-UINT+1 MID-UINT+1 WITHIN -> FALSE }T
+T{ 0 MID-UINT+1 MAX-UINT WITHIN -> FALSE }T
+T{ 0 MAX-UINT 0 WITHIN -> FALSE }T
+T{ 0 MAX-UINT MID-UINT WITHIN -> TRUE }T
+T{ 0 MAX-UINT MID-UINT+1 WITHIN -> TRUE }T
+T{ 0 MAX-UINT MAX-UINT WITHIN -> FALSE }T
+T{ MID-UINT 0 0 WITHIN -> FALSE }T
+T{ MID-UINT 0 MID-UINT WITHIN -> FALSE }T
+T{ MID-UINT 0 MID-UINT+1 WITHIN -> TRUE }T
+T{ MID-UINT 0 MAX-UINT WITHIN -> TRUE }T
+T{ MID-UINT MID-UINT 0 WITHIN -> TRUE }T
+T{ MID-UINT MID-UINT MID-UINT WITHIN -> FALSE }T
+T{ MID-UINT MID-UINT MID-UINT+1 WITHIN -> TRUE }T
+T{ MID-UINT MID-UINT MAX-UINT WITHIN -> TRUE }T
+T{ MID-UINT MID-UINT+1 0 WITHIN -> FALSE }T
+T{ MID-UINT MID-UINT+1 MID-UINT WITHIN -> FALSE }T
+T{ MID-UINT MID-UINT+1 MID-UINT+1 WITHIN -> FALSE }T
+T{ MID-UINT MID-UINT+1 MAX-UINT WITHIN -> FALSE }T
+T{ MID-UINT MAX-UINT 0 WITHIN -> FALSE }T
+T{ MID-UINT MAX-UINT MID-UINT WITHIN -> FALSE }T
+T{ MID-UINT MAX-UINT MID-UINT+1 WITHIN -> TRUE }T
+T{ MID-UINT MAX-UINT MAX-UINT WITHIN -> FALSE }T
+T{ MID-UINT+1 0 0 WITHIN -> FALSE }T
+T{ MID-UINT+1 0 MID-UINT WITHIN -> FALSE }T
+T{ MID-UINT+1 0 MID-UINT+1 WITHIN -> FALSE }T
+T{ MID-UINT+1 0 MAX-UINT WITHIN -> TRUE }T
+T{ MID-UINT+1 MID-UINT 0 WITHIN -> TRUE }T
+T{ MID-UINT+1 MID-UINT MID-UINT WITHIN -> FALSE }T
+T{ MID-UINT+1 MID-UINT MID-UINT+1 WITHIN -> FALSE }T
+T{ MID-UINT+1 MID-UINT MAX-UINT WITHIN -> TRUE }T
+T{ MID-UINT+1 MID-UINT+1 0 WITHIN -> TRUE }T
+T{ MID-UINT+1 MID-UINT+1 MID-UINT WITHIN -> TRUE }T
+T{ MID-UINT+1 MID-UINT+1 MID-UINT+1 WITHIN -> FALSE }T
+T{ MID-UINT+1 MID-UINT+1 MAX-UINT WITHIN -> TRUE }T
+T{ MID-UINT+1 MAX-UINT 0 WITHIN -> FALSE }T
+T{ MID-UINT+1 MAX-UINT MID-UINT WITHIN -> FALSE }T
+T{ MID-UINT+1 MAX-UINT MID-UINT+1 WITHIN -> FALSE }T
+T{ MID-UINT+1 MAX-UINT MAX-UINT WITHIN -> FALSE }T
+T{ MAX-UINT 0 0 WITHIN -> FALSE }T
+T{ MAX-UINT 0 MID-UINT WITHIN -> FALSE }T
+T{ MAX-UINT 0 MID-UINT+1 WITHIN -> FALSE }T
+T{ MAX-UINT 0 MAX-UINT WITHIN -> FALSE }T
+T{ MAX-UINT MID-UINT 0 WITHIN -> TRUE }T
+T{ MAX-UINT MID-UINT MID-UINT WITHIN -> FALSE }T
+T{ MAX-UINT MID-UINT MID-UINT+1 WITHIN -> FALSE }T
+T{ MAX-UINT MID-UINT MAX-UINT WITHIN -> FALSE }T
+T{ MAX-UINT MID-UINT+1 0 WITHIN -> TRUE }T
+T{ MAX-UINT MID-UINT+1 MID-UINT WITHIN -> TRUE }T
+T{ MAX-UINT MID-UINT+1 MID-UINT+1 WITHIN -> FALSE }T
+T{ MAX-UINT MID-UINT+1 MAX-UINT WITHIN -> FALSE }T
+T{ MAX-UINT MAX-UINT 0 WITHIN -> TRUE }T
+T{ MAX-UINT MAX-UINT MID-UINT WITHIN -> TRUE }T
+T{ MAX-UINT MAX-UINT MID-UINT+1 WITHIN -> TRUE }T
+T{ MAX-UINT MAX-UINT MAX-UINT WITHIN -> FALSE }T
+
+T{ MIN-INT MIN-INT MIN-INT WITHIN -> FALSE }T
+T{ MIN-INT MIN-INT 0 WITHIN -> TRUE }T
+T{ MIN-INT MIN-INT 1 WITHIN -> TRUE }T
+T{ MIN-INT MIN-INT MAX-INT WITHIN -> TRUE }T
+T{ MIN-INT 0 MIN-INT WITHIN -> FALSE }T
+T{ MIN-INT 0 0 WITHIN -> FALSE }T
+T{ MIN-INT 0 1 WITHIN -> FALSE }T
+T{ MIN-INT 0 MAX-INT WITHIN -> FALSE }T
+T{ MIN-INT 1 MIN-INT WITHIN -> FALSE }T
+T{ MIN-INT 1 0 WITHIN -> TRUE }T
+T{ MIN-INT 1 1 WITHIN -> FALSE }T
+T{ MIN-INT 1 MAX-INT WITHIN -> FALSE }T
+T{ MIN-INT MAX-INT MIN-INT WITHIN -> FALSE }T
+T{ MIN-INT MAX-INT 0 WITHIN -> TRUE }T
+T{ MIN-INT MAX-INT 1 WITHIN -> TRUE }T
+T{ MIN-INT MAX-INT MAX-INT WITHIN -> FALSE }T
+T{ 0 MIN-INT MIN-INT WITHIN -> FALSE }T
+T{ 0 MIN-INT 0 WITHIN -> FALSE }T
+T{ 0 MIN-INT 1 WITHIN -> TRUE }T
+T{ 0 MIN-INT MAX-INT WITHIN -> TRUE }T
+T{ 0 0 MIN-INT WITHIN -> TRUE }T
+T{ 0 0 0 WITHIN -> FALSE }T
+T{ 0 0 1 WITHIN -> TRUE }T
+T{ 0 0 MAX-INT WITHIN -> TRUE }T
+T{ 0 1 MIN-INT WITHIN -> FALSE }T
+T{ 0 1 0 WITHIN -> FALSE }T
+T{ 0 1 1 WITHIN -> FALSE }T
+T{ 0 1 MAX-INT WITHIN -> FALSE }T
+T{ 0 MAX-INT MIN-INT WITHIN -> FALSE }T
+T{ 0 MAX-INT 0 WITHIN -> FALSE }T
+T{ 0 MAX-INT 1 WITHIN -> TRUE }T
+T{ 0 MAX-INT MAX-INT WITHIN -> FALSE }T
+T{ 1 MIN-INT MIN-INT WITHIN -> FALSE }T
+T{ 1 MIN-INT 0 WITHIN -> FALSE }T
+T{ 1 MIN-INT 1 WITHIN -> FALSE }T
+T{ 1 MIN-INT MAX-INT WITHIN -> TRUE }T
+T{ 1 0 MIN-INT WITHIN -> TRUE }T
+T{ 1 0 0 WITHIN -> FALSE }T
+T{ 1 0 1 WITHIN -> FALSE }T
+T{ 1 0 MAX-INT WITHIN -> TRUE }T
+T{ 1 1 MIN-INT WITHIN -> TRUE }T
+T{ 1 1 0 WITHIN -> TRUE }T
+T{ 1 1 1 WITHIN -> FALSE }T
+T{ 1 1 MAX-INT WITHIN -> TRUE }T
+T{ 1 MAX-INT MIN-INT WITHIN -> FALSE }T
+T{ 1 MAX-INT 0 WITHIN -> FALSE }T
+T{ 1 MAX-INT 1 WITHIN -> FALSE }T
+T{ 1 MAX-INT MAX-INT WITHIN -> FALSE }T
+T{ MAX-INT MIN-INT MIN-INT WITHIN -> FALSE }T
+T{ MAX-INT MIN-INT 0 WITHIN -> FALSE }T
+T{ MAX-INT MIN-INT 1 WITHIN -> FALSE }T
+T{ MAX-INT MIN-INT MAX-INT WITHIN -> FALSE }T
+T{ MAX-INT 0 MIN-INT WITHIN -> TRUE }T
+T{ MAX-INT 0 0 WITHIN -> FALSE }T
+T{ MAX-INT 0 1 WITHIN -> FALSE }T
+T{ MAX-INT 0 MAX-INT WITHIN -> FALSE }T
+T{ MAX-INT 1 MIN-INT WITHIN -> TRUE }T
+T{ MAX-INT 1 0 WITHIN -> TRUE }T
+T{ MAX-INT 1 1 WITHIN -> FALSE }T
+T{ MAX-INT 1 MAX-INT WITHIN -> FALSE }T
+T{ MAX-INT MAX-INT MIN-INT WITHIN -> TRUE }T
+T{ MAX-INT MAX-INT 0 WITHIN -> TRUE }T
+T{ MAX-INT MAX-INT 1 WITHIN -> TRUE }T
+T{ MAX-INT MAX-INT MAX-INT WITHIN -> FALSE }T
+
+\ -----------------------------------------------------------------------------
+TESTING UNUSED  (contributed by James Bowman & Peter Knaggs)
+
+VARIABLE UNUSED0
+T{ UNUSED DROP -> }T                  
+T{ ALIGN UNUSED UNUSED0 ! 0 , UNUSED CELL+ UNUSED0 @ = -> TRUE }T
+T{ UNUSED UNUSED0 ! 0 C, UNUSED CHAR+ UNUSED0 @ =
+         -> TRUE }T  \ aligned -> unaligned
+T{ UNUSED UNUSED0 ! 0 C, UNUSED CHAR+ UNUSED0 @ = -> TRUE }T  \ unaligned -> ?
+
+\ -----------------------------------------------------------------------------
+TESTING AGAIN   (contributed by James Bowman)
+
+T{ : AG0 701 BEGIN DUP 7 MOD 0= IF EXIT THEN 1+ AGAIN ; -> }T
+T{ AG0 -> 707 }T
+
+\ -----------------------------------------------------------------------------
+TESTING MARKER   (contributed by James Bowman)
+
+T{ : MA? BL WORD FIND NIP 0<> ; -> }T
+T{ MARKER MA0 -> }T
+T{ : MA1 111 ; -> }T
+T{ MARKER MA2 -> }T
+T{ : MA1 222 ; -> }T
+T{ MA? MA0 MA? MA1 MA? MA2 -> TRUE TRUE TRUE }T
+T{ MA1 MA2 MA1 -> 222 111 }T
+T{ MA? MA0 MA? MA1 MA? MA2 -> TRUE TRUE FALSE }T
+T{ MA0 -> }T
+T{ MA? MA0 MA? MA1 MA? MA2 -> FALSE FALSE FALSE }T
+
+\ -----------------------------------------------------------------------------
+TESTING ?DO
+
+: QD ?DO I LOOP ;
+T{ 789 789 QD -> }T
+T{ -9876 -9876 QD -> }T
+T{ 5 0 QD -> 0 1 2 3 4 }T
+
+: QD1 ?DO I 10 +LOOP ;
+T{ 50 1 QD1 -> 1 11 21 31 41 }T
+T{ 50 0 QD1 -> 0 10 20 30 40 }T
+
+: QD2 ?DO I 3 > IF LEAVE ELSE I THEN LOOP ;
+T{ 5 -1 QD2 -> -1 0 1 2 3 }T
+
+: QD3 ?DO I 1 +LOOP ;
+T{ 4  4 QD3 -> }T
+T{ 4  1 QD3 -> 1 2 3 }T
+T{ 2 -1 QD3 -> -1 0 1 }T
+
+: QD4 ?DO I -1 +LOOP ;
+T{  4 4 QD4 -> }T
+T{  1 4 QD4 -> 4 3 2 1 }T
+T{ -1 2 QD4 -> 2 1 0 -1 }T
+
+: QD5 ?DO I -10 +LOOP ;
+T{   1 50 QD5 -> 50 40 30 20 10 }T
+T{   0 50 QD5 -> 50 40 30 20 10 0 }T
+T{ -25 10 QD5 -> 10 0 -10 -20 }T
+
+VARIABLE ITERS
+VARIABLE INCRMNT
+
+: QD6 ( limit start increment -- )
+   INCRMNT !
+   0 ITERS !
+   ?DO
+      1 ITERS +!
+      I
+      ITERS @  6 = IF LEAVE THEN
+      INCRMNT @
+   +LOOP ITERS @
+;
+
+T{  4  4 -1 QD6 -> 0 }T
+T{  1  4 -1 QD6 -> 4 3 2 1 4 }T
+T{  4  1 -1 QD6 -> 1 0 -1 -2 -3 -4 6 }T
+T{  4  1  0 QD6 -> 1 1 1 1 1 1 6 }T
+T{  0  0  0 QD6 -> 0 }T
+T{  1  4  0 QD6 -> 4 4 4 4 4 4 6 }T
+T{  1  4  1 QD6 -> 4 5 6 7 8 9 6 }T
+T{  4  1  1 QD6 -> 1 2 3 3 }T
+T{  4  4  1 QD6 -> 0 }T
+T{  2 -1 -1 QD6 -> -1 -2 -3 -4 -5 -6 6 }T
+T{ -1  2 -1 QD6 -> 2 1 0 -1 4 }T
+T{  2 -1  0 QD6 -> -1 -1 -1 -1 -1 -1 6 }T
+T{ -1  2  0 QD6 -> 2 2 2 2 2 2 6 }T
+T{ -1  2  1 QD6 -> 2 3 4 5 6 7 6 }T
+T{  2 -1  1 QD6 -> -1 0 1 3 }T
+
+\ -----------------------------------------------------------------------------
+TESTING BUFFER:
+
+T{ 2 CELLS BUFFER: BUF:TEST -> }T
+T{ BUF:TEST DUP ALIGNED = -> TRUE }T
+T{ 111 BUF:TEST ! 222 BUF:TEST CELL+ ! -> }T
+T{ BUF:TEST @ BUF:TEST CELL+ @ -> 111 222 }T
+
+\ -----------------------------------------------------------------------------
+TESTING VALUE TO
+
+T{ 111 VALUE VAL1 -999 VALUE VAL2 -> }T
+T{ VAL1 -> 111 }T
+T{ VAL2 -> -999 }T
+T{ 222 TO VAL1 -> }T
+T{ VAL1 -> 222 }T
+T{ : VD1 VAL1 ; -> }T
+T{ VD1 -> 222 }T
+T{ : VD2 TO VAL2 ; -> }T
+T{ VAL2 -> -999 }T
+T{ -333 VD2 -> }T
+T{ VAL2 -> -333 }T
+T{ VAL1 -> 222 }T
+T{ 444 TO VAL1 -> }T
+T{ VD1 -> 444 }T
+T{ 123 VALUE VAL3 IMMEDIATE VAL3 -> 123 }T
+T{ : VD3 VAL3 LITERAL ; VD3 -> 123 }T
+
+\ -----------------------------------------------------------------------------
+TESTING CASE OF ENDOF ENDCASE
+
+: CS1 CASE 1 OF 111 ENDOF
+           2 OF 222 ENDOF
+           3 OF 333 ENDOF
+           >R 999 R>
+      ENDCASE
+;
+
+T{ 1 CS1 -> 111 }T
+T{ 2 CS1 -> 222 }T
+T{ 3 CS1 -> 333 }T
+T{ 4 CS1 -> 999 }T
+
+\ Nested CASE's
+
+: CS2 >R CASE -1 OF CASE R@ 1 OF 100 ENDOF
+                            2 OF 200 ENDOF
+                           >R -300 R>
+                    ENDCASE
+                 ENDOF
+              -2 OF CASE R@ 1 OF -99  ENDOF
+                            >R -199 R>
+                    ENDCASE
+                 ENDOF
+                 >R 299 R>
+         ENDCASE R> DROP
+;
+
+T{ -1 1 CS2 ->  100 }T
+T{ -1 2 CS2 ->  200 }T
+T{ -1 3 CS2 -> -300 }T
+T{ -2 1 CS2 -> -99  }T
+T{ -2 2 CS2 -> -199 }T
+T{  0 2 CS2 ->  299 }T
+
+\ Boolean short circuiting using CASE
+
+: CS3  ( N1 -- N2 )
+   CASE 1- FALSE OF 11 ENDOF
+        1- FALSE OF 22 ENDOF
+        1- FALSE OF 33 ENDOF
+        44 SWAP
+   ENDCASE
+;
+
+T{ 1 CS3 -> 11 }T
+T{ 2 CS3 -> 22 }T
+T{ 3 CS3 -> 33 }T
+T{ 9 CS3 -> 44 }T
+
+\ Empty CASE statements with/without default
+
+T{ : CS4 CASE ENDCASE ; 1 CS4 -> }T
+T{ : CS5 CASE 2 SWAP ENDCASE ; 1 CS5 -> 2 }T
+T{ : CS6 CASE 1 OF ENDOF 2 ENDCASE ; 1 CS6 -> }T
+T{ : CS7 CASE 3 OF ENDOF 2 ENDCASE ; 1 CS7 -> 1 }T
+
+\ -----------------------------------------------------------------------------
+TESTING :NONAME RECURSE
+
+VARIABLE NN1
+VARIABLE NN2
+:NONAME 1234 ; NN1 !
+:NONAME 9876 ; NN2 !
+T{ NN1 @ EXECUTE -> 1234 }T
+T{ NN2 @ EXECUTE -> 9876 }T
+
+T{ :NONAME ( n -- 0,1,..n ) DUP IF DUP >R 1- RECURSE R> THEN ;
+   CONSTANT RN1 -> }T
+T{ 0 RN1 EXECUTE -> 0 }T
+T{ 4 RN1 EXECUTE -> 0 1 2 3 4 }T
+
+:NONAME  ( n -- n1 )    \ Multiple RECURSEs in one definition
+   1- DUP
+   CASE 0 OF EXIT ENDOF
+        1 OF 11 SWAP RECURSE ENDOF
+        2 OF 22 SWAP RECURSE ENDOF
+        3 OF 33 SWAP RECURSE ENDOF
+        DROP ABS RECURSE EXIT
+   ENDCASE
+; CONSTANT RN2
+
+T{  1 RN2 EXECUTE -> 0 }T
+T{  2 RN2 EXECUTE -> 11 0 }T
+T{  4 RN2 EXECUTE -> 33 22 11 0 }T
+T{ 25 RN2 EXECUTE -> 33 22 11 0 }T
+
+\ -----------------------------------------------------------------------------
+TESTING C"
+
+T{ : CQ1 C" 123" ; -> }T
+T{ CQ1 COUNT EVALUATE -> 123 }T
+T{ : CQ2 C" " ; -> }T
+T{ CQ2 COUNT EVALUATE -> }T
+T{ : CQ3 C" 2345"COUNT EVALUATE ; CQ3 -> 2345 }T
+
+\ -----------------------------------------------------------------------------
+TESTING COMPILE,
+
+:NONAME DUP + ; CONSTANT DUP+
+T{ : Q DUP+ COMPILE, ; -> }T
+T{ : AS1 [ Q ] ; -> }T
+T{ 123 AS1 -> 246 }T
+
+\ -----------------------------------------------------------------------------
+\ Cannot automatically test SAVE-INPUT and RESTORE-INPUT from a console source
+
+TESTING SAVE-INPUT and RESTORE-INPUT with a string source
+
+VARIABLE SI_INC 0 SI_INC !
+
+: SI1
+   SI_INC @ >IN +!
+   15 SI_INC !
+;
+
+: S$ S" SAVE-INPUT SI1 RESTORE-INPUT 12345" ;
+
+T{ S$ EVALUATE SI_INC @ -> 0 2345 15 }T
+
+\ -----------------------------------------------------------------------------
+TESTING .(
+
+CR CR .( Output from .() 
+T{ CR .( You should see -9876: ) -9876 . -> }T
+T{ CR .( and again: ).( -9876)CR -> }T
+
+CR CR .( On the next 2 lines you should see First then Second messages:)
+T{ : DOTP  CR ." Second message via ." [CHAR] " EMIT    \ Check .( is immediate
+     [ CR ] .( First message via .( ) ; DOTP -> }T
+CR CR
+T{ : IMM? BL WORD FIND NIP ; IMM? .( -> 1 }T
+
+\ -----------------------------------------------------------------------------
+TESTING .R and U.R - has to handle different cell sizes
+
+\ Create some large integers just below/above MAX and Min INTs
+MAX-INT 73 79 */ CONSTANT LI1
+MIN-INT 71 73 */ CONSTANT LI2
+
+LI1 0 <# #S #> NIP CONSTANT LENLI1
+
+: (.R&U.R)  ( u1 u2 -- )  \ u1 <= string length, u2 is required indentation
+   TUCK + >R
+   LI1 OVER SPACES  . CR R@    LI1 SWAP  .R CR
+   LI2 OVER SPACES  . CR R@ 1+ LI2 SWAP  .R CR
+   LI1 OVER SPACES U. CR R@    LI1 SWAP U.R CR
+   LI2 SWAP SPACES U. CR R>    LI2 SWAP U.R CR
+;
+
+: .R&U.R  ( -- )
+   CR ." You should see lines duplicated:" CR
+   ." indented by 0 spaces" CR 0      0 (.R&U.R) CR
+   ." indented by 0 spaces" CR LENLI1 0 (.R&U.R) CR \ Just fits required width
+   ." indented by 5 spaces" CR LENLI1 5 (.R&U.R) CR
+;
+
+CR CR .( Output from .R and U.R)
+T{ .R&U.R -> }T
+
+\ -----------------------------------------------------------------------------
+TESTING PAD ERASE
+\ Must handle different size characters i.e. 1 CHARS >= 1 
+
+84 CONSTANT CHARS/PAD      \ Minimum size of PAD in chars
+CHARS/PAD CHARS CONSTANT AUS/PAD
+: CHECKPAD  ( caddr u ch -- f )  \ f = TRUE if u chars = ch
+   SWAP 0
+   ?DO
+      OVER I CHARS + C@ OVER <>
+      IF 2DROP UNLOOP FALSE EXIT THEN
+   LOOP  
+   2DROP TRUE
+;
+
+T{ PAD DROP -> }T
+T{ 0 INVERT PAD C! -> }T
+T{ PAD C@ CONSTANT MAXCHAR -> }T
+T{ PAD CHARS/PAD 2DUP MAXCHAR FILL MAXCHAR CHECKPAD -> TRUE }T
+T{ PAD CHARS/PAD 2DUP CHARS ERASE 0 CHECKPAD -> TRUE }T
+T{ PAD CHARS/PAD 2DUP MAXCHAR FILL PAD 0 ERASE MAXCHAR CHECKPAD -> TRUE }T
+T{ PAD 43 CHARS + 9 CHARS ERASE -> }T
+T{ PAD 43 MAXCHAR CHECKPAD -> TRUE }T
+T{ PAD 43 CHARS + 9 0 CHECKPAD -> TRUE }T
+T{ PAD 52 CHARS + CHARS/PAD 52 - MAXCHAR CHECKPAD -> TRUE }T
+
+\ Check that use of WORD and pictured numeric output do not corrupt PAD
+\ Minimum size of buffers for these are 33 chars and (2*n)+2 chars respectively
+\ where n is number of bits per cell
+
+PAD CHARS/PAD ERASE
+2 BASE !
+MAX-UINT MAX-UINT <# #S CHAR 1 DUP HOLD HOLD #> 2DROP
+DECIMAL
+BL WORD 12345678123456781234567812345678 DROP
+T{ PAD CHARS/PAD 0 CHECKPAD -> TRUE }T
+
+\ -----------------------------------------------------------------------------
+TESTING PARSE
+
+T{ CHAR | PARSE 1234| DUP ROT ROT EVALUATE -> 4 1234 }T
+T{ CHAR ^ PARSE  23 45 ^ DUP ROT ROT EVALUATE -> 7 23 45 }T
+: PA1 [CHAR] $ PARSE DUP >R PAD SWAP CHARS MOVE PAD R> ;
+T{ PA1 3456
+   DUP ROT ROT EVALUATE -> 4 3456 }T
+T{ CHAR A PARSE A SWAP DROP -> 0 }T
+T{ CHAR Z PARSE
+   SWAP DROP -> 0 }T
+T{ CHAR " PARSE 4567 "DUP ROT ROT EVALUATE -> 5 4567 }T
+ 
+\ -----------------------------------------------------------------------------
+TESTING PARSE-NAME  (Forth 2012)
+\ Adapted from the PARSE-NAME RfD tests
+
+T{ PARSE-NAME abcd  STR1  S= -> TRUE }T        \ No leading spaces
+T{ PARSE-NAME      abcde STR2 S= -> TRUE }T    \ Leading spaces
+
+\ Test empty parse area, new lines are necessary
+T{ PARSE-NAME
+  NIP -> 0 }T
+\ Empty parse area with spaces after PARSE-NAME
+T{ PARSE-NAME         
+  NIP -> 0 }T
+
+T{ : PARSE-NAME-TEST ( "name1" "name2" -- n )
+    PARSE-NAME PARSE-NAME S= ; -> }T
+T{ PARSE-NAME-TEST abcd abcd  -> TRUE }T
+T{ PARSE-NAME-TEST abcd   abcd  -> TRUE }T  \ Leading spaces
+T{ PARSE-NAME-TEST abcde abcdf -> FALSE }T
+T{ PARSE-NAME-TEST abcdf abcde -> FALSE }T
+T{ PARSE-NAME-TEST abcde abcde
+   -> TRUE }T         \ Parse to end of line
+T{ PARSE-NAME-TEST abcde           abcde         
+   -> TRUE }T         \ Leading and trailing spaces
+
+\ -----------------------------------------------------------------------------
+TESTING DEFER DEFER@ DEFER! IS ACTION-OF (Forth 2012)
+\ Adapted from the Forth 200X RfD tests
+
+T{ DEFER DEFER1 -> }T
+T{ : MY-DEFER DEFER ; -> }T
+T{ : IS-DEFER1 IS DEFER1 ; -> }T
+T{ : ACTION-DEFER1 ACTION-OF DEFER1 ; -> }T
+T{ : DEF! DEFER! ; -> }T
+T{ : DEF@ DEFER@ ; -> }T
+
+T{ ' * ' DEFER1 DEFER! -> }T
+T{ 2 3 DEFER1 -> 6 }T
+T{ ' DEFER1 DEFER@ -> ' * }T
+T{ ' DEFER1 DEF@ -> ' * }T
+T{ ACTION-OF DEFER1 -> ' * }T
+T{ ACTION-DEFER1 -> ' * }T
+T{ ' + IS DEFER1 -> }T
+T{ 1 2 DEFER1 -> 3 }T
+T{ ' DEFER1 DEFER@ -> ' + }T
+T{ ' DEFER1 DEF@ -> ' + }T
+T{ ACTION-OF DEFER1 -> ' + }T
+T{ ACTION-DEFER1 -> ' + }T
+T{ ' - IS-DEFER1 -> }T
+T{ 1 2 DEFER1 -> -1 }T
+T{ ' DEFER1 DEFER@ -> ' - }T
+T{ ' DEFER1 DEF@ -> ' - }T
+T{ ACTION-OF DEFER1 -> ' - }T
+T{ ACTION-DEFER1 -> ' - }T
+
+T{ MY-DEFER DEFER2 -> }T
+T{ ' DUP IS DEFER2 -> }T
+T{ 1 DEFER2 -> 1 1 }T
+
+\ -----------------------------------------------------------------------------
+TESTING HOLDS  (Forth 2012)
+
+: HTEST S" Testing HOLDS" ;
+: HTEST2 S" works" ;
+: HTEST3 S" Testing HOLDS works 123" ;
+T{ 0 0 <#  HTEST HOLDS #> HTEST S= -> TRUE }T
+T{ 123 0 <# #S BL HOLD HTEST2 HOLDS BL HOLD HTEST HOLDS #>
+   HTEST3 S= -> TRUE }T
+T{ : HLD HOLDS ; -> }T
+T{ 0 0 <#  HTEST HLD #> HTEST S= -> TRUE }T
+
+\ -----------------------------------------------------------------------------
+TESTING REFILL SOURCE-ID
+\ REFILL and SOURCE-ID from the user input device can't be tested from a file,
+\ can only be tested from a string via EVALUATE
+
+T{ : RF1  S" REFILL" EVALUATE ; RF1 -> FALSE }T
+T{ : SID1  S" SOURCE-ID" EVALUATE ; SID1 -> -1 }T
+
+\ ------------------------------------------------------------------------------
+TESTING S\"  (Forth 2012 compilation mode)
+\ Extended the Forth 200X RfD tests
+\ Note this tests the Core Ext definition of S\" which has unedfined
+\ interpretation semantics. S\" in interpretation mode is tested in the tests on
+\ the File-Access word set
+
+T{ : SSQ1 S\" abc" S" abc" S= ; -> }T  \ No escapes
+T{ SSQ1 -> TRUE }T
+T{ : SSQ2 S\" " ; SSQ2 SWAP DROP -> 0 }T    \ Empty string
+
+T{ : SSQ3 S\" \a\b\e\f\l\m\q\r\t\v\x0F0\x1Fa\xaBx\z\"\\" ; -> }T
+T{ SSQ3 SWAP DROP          ->  20 }T    \ String length
+T{ SSQ3 DROP            C@ ->   7 }T    \ \a   BEL  Bell
+T{ SSQ3 DROP  1 CHARS + C@ ->   8 }T    \ \b   BS   Backspace
+T{ SSQ3 DROP  2 CHARS + C@ ->  27 }T    \ \e   ESC  Escape
+T{ SSQ3 DROP  3 CHARS + C@ ->  12 }T    \ \f   FF   Form feed
+T{ SSQ3 DROP  4 CHARS + C@ ->  10 }T    \ \l   LF   Line feed
+T{ SSQ3 DROP  5 CHARS + C@ ->  13 }T    \ \m        CR of CR/LF pair
+T{ SSQ3 DROP  6 CHARS + C@ ->  10 }T    \           LF of CR/LF pair
+T{ SSQ3 DROP  7 CHARS + C@ ->  34 }T    \ \q   "    Double Quote
+T{ SSQ3 DROP  8 CHARS + C@ ->  13 }T    \ \r   CR   Carriage Return
+T{ SSQ3 DROP  9 CHARS + C@ ->   9 }T    \ \t   TAB  Horizontal Tab
+T{ SSQ3 DROP 10 CHARS + C@ ->  11 }T    \ \v   VT   Vertical Tab
+T{ SSQ3 DROP 11 CHARS + C@ ->  15 }T    \ \x0F      Given Char
+T{ SSQ3 DROP 12 CHARS + C@ ->  48 }T    \ 0    0    Digit follow on
+T{ SSQ3 DROP 13 CHARS + C@ ->  31 }T    \ \x1F      Given Char
+T{ SSQ3 DROP 14 CHARS + C@ ->  97 }T    \ a    a    Hex follow on
+T{ SSQ3 DROP 15 CHARS + C@ -> 171 }T    \ \xaB      Insensitive Given Char
+T{ SSQ3 DROP 16 CHARS + C@ -> 120 }T    \ x    x    Non hex follow on
+T{ SSQ3 DROP 17 CHARS + C@ ->   0 }T    \ \z   NUL  No Character
+T{ SSQ3 DROP 18 CHARS + C@ ->  34 }T    \ \"   "    Double Quote
+T{ SSQ3 DROP 19 CHARS + C@ ->  92 }T    \ \\   \    Back Slash
+
+\ The above does not test \n as this is a system dependent value.
+\ Check it displays a new line
+CR .( The next test should display:)
+CR .( One line...)
+CR .( another line)
+T{ : SSQ4 S\" \nOne line...\nanotherLine\n" TYPE ; SSQ4 -> }T
+
+\ Test bare escapable characters appear as themselves
+T{ : SSQ5 S\" abeflmnqrtvxz" S" abeflmnqrtvxz" S= ; SSQ5 -> TRUE }T
+
+T{ : SSQ6 S\" a\""2DROP 1111 ; SSQ6 -> 1111 }T \ Parsing behaviour
+
+T{ : SSQ7  S\" 111 : SSQ8 S\\\" 222\" EVALUATE ; SSQ8 333" EVALUATE ; -> }T
+T{ SSQ7 -> 111 222 333 }T
+T{ : SSQ9  S\" 11 : SSQ10 S\\\" \\x32\\x32\" EVALUATE ; SSQ10 33" EVALUATE ; -> }T
+T{ SSQ9 -> 11 22 33 }T
+
+\ -----------------------------------------------------------------------------
+CORE-EXT-ERRORS SET-ERROR-COUNT
+
+CR .( End of Core Extension word tests) CR
+
+
--- a/lib/forth/ans-tests/tester.fr
+++ b/lib/forth/ans-tests/tester.fr
@@ -0,0 +1,66 @@
+\ From: John Hayes S1I
+\ Subject: tester.fr
+\ Date: Mon, 27 Nov 95 13:10:09 PST  
+
+\ (C) 1995 JOHNS HOPKINS UNIVERSITY / APPLIED PHYSICS LABORATORY
+\ MAY BE DISTRIBUTED FREELY AS LONG AS THIS COPYRIGHT NOTICE REMAINS.
+\ VERSION 1.2
+
+\ 24/11/2015 Replaced Core Ext word <> with = 0=
+\ 31/3/2015 Variable #ERRORS added and incremented for each error reported.
+\ 22/1/09 The words { and } have been changed to T{ and }T respectively to
+\ agree with the Forth 200X file ttester.fs. This avoids clashes with
+\ locals using { ... } and the FSL use of } 
+
+HEX
+
+\ SET THE FOLLOWING FLAG TO TRUE FOR MORE VERBOSE OUTPUT; THIS MAY
+\ ALLOW YOU TO TELL WHICH TEST CAUSED YOUR SYSTEM TO HANG.
+VARIABLE VERBOSE
+   FALSE VERBOSE !
+\   TRUE VERBOSE !
+
+: EMPTY-STACK   \ ( ... -- ) EMPTY STACK: HANDLES UNDERFLOWED STACK TOO.
+   DEPTH ?DUP IF DUP 0< IF NEGATE 0 DO 0 LOOP ELSE 0 DO DROP LOOP THEN THEN ;
+
+VARIABLE #ERRORS 0 #ERRORS !
+
+: ERROR      \ ( C-ADDR U -- ) DISPLAY AN ERROR MESSAGE FOLLOWED BY
+      \ THE LINE THAT HAD THE ERROR.
+   CR TYPE SOURCE TYPE       \ DISPLAY LINE CORRESPONDING TO ERROR
+   EMPTY-STACK               \ THROW AWAY EVERY THING ELSE
+   #ERRORS @ 1 + #ERRORS !
+\   QUIT  \ *** Uncomment this line to QUIT on an error
+;
+
+VARIABLE ACTUAL-DEPTH         \ STACK RECORD
+CREATE ACTUAL-RESULTS 20 CELLS ALLOT
+
+: T{      \ ( -- ) SYNTACTIC SUGAR.
+   ;
+
+: ->      \ ( ... -- ) RECORD DEPTH AND CONTENT OF STACK.
+   DEPTH DUP ACTUAL-DEPTH !      \ RECORD DEPTH
+   ?DUP IF            \ IF THERE IS SOMETHING ON STACK
+      0 DO ACTUAL-RESULTS I CELLS + ! LOOP \ SAVE THEM
+   THEN ;
+
+: }T      \ ( ... -- ) COMPARE STACK (EXPECTED) CONTENTS WITH SAVED
+      \ (ACTUAL) CONTENTS.
+   DEPTH ACTUAL-DEPTH @ = IF      \ IF DEPTHS MATCH
+      DEPTH ?DUP IF         \ IF THERE IS SOMETHING ON THE STACK
+         0  DO            \ FOR EACH STACK ITEM
+           ACTUAL-RESULTS I CELLS + @   \ COMPARE ACTUAL WITH EXPECTED
+           = 0= IF S" INCORRECT RESULT: " ERROR LEAVE THEN
+         LOOP
+      THEN
+   ELSE               \ DEPTH MISMATCH
+      S" WRONG NUMBER OF RESULTS: " ERROR
+   THEN ;
+
+: TESTING   \ ( -- ) TALKING COMMENT.
+  SOURCE VERBOSE @
+   IF DUP >R TYPE CR R> >IN !
+   ELSE >IN ! DROP [CHAR] * EMIT
+   THEN ;
+
--- a/lib/forth/compiler.sx
+++ b/lib/forth/compiler.sx
--- a/lib/forth/conformance.sh
+++ b/lib/forth/conformance.sh
@@ -0,0 +1,170 @@
+#!/usr/bin/env bash
+# Run the Hayes/Gerry-Jackson Core conformance suite against our Forth
+# interpreter and emit scoreboard.json + scoreboard.md.
+#
+# Method:
+#   1. Preprocess lib/forth/ans-tests/core.fr — strip \ comments, ( ... )
+#      comments, and TESTING … metadata lines.
+#   2. Split into chunks ending at each `}T` so an error in one test
+#      chunk doesn't abort the run.
+#   3. Emit an SX file that exposes those chunks as a list.
+#   4. Run our Forth + hayes-runner under sx_server; record pass/fail/error.
+
+set -e
+FORTH_DIR="$(cd "$(dirname "$0")" && pwd)"
+ROOT="$(cd "$FORTH_DIR/../.." && pwd)"
+SX_SERVER="${SX_SERVER:-/root/rose-ash/hosts/ocaml/_build/default/bin/sx_server.exe}"
+SOURCE="$FORTH_DIR/ans-tests/core.fr"
+OUT_JSON="$FORTH_DIR/scoreboard.json"
+OUT_MD="$FORTH_DIR/scoreboard.md"
+TMP="$(mktemp -d)"
+PREPROC="$TMP/preproc.forth"
+CHUNKS_SX="$TMP/chunks.sx"
+
+cd "$ROOT"
+
+# 1. preprocess
+awk '
+{
+  line = $0
+  # protect POSTPONE \ so the comment-strip below leaves the literal \ alone
+  gsub(/POSTPONE[ \t]+\\/, "POSTPONE @@BS@@", line)
+  # strip leading/embedded \ line comments (must be \ followed by space or EOL)
+  gsub(/(^|[ \t])\\([ \t].*|$)/, " ", line)
+  # strip ( ... ) block comments that sit on one line
+  gsub(/\([^)]*\)/, " ", line)
+  # strip TESTING … metadata lines (rest of line, incl. bare TESTING)
+  sub(/TESTING([ \t].*)?$/, " ", line)
+  # restore the protected backslash
+  gsub(/@@BS@@/, "\\", line)
+  print line
+}' "$SOURCE" > "$PREPROC"
+
+# 2 + 3: split into chunks at each `}T` and emit as a SX file
+#
+# Cap chunks via MAX_CHUNKS env (default 638 = full Hayes Core). Lower
+# it temporarily if later tests regress into an infinite loop while you
+# are iterating on primitives.
+MAX_CHUNKS="${MAX_CHUNKS:-638}"
+
+MAX_CHUNKS="$MAX_CHUNKS" python3 - "$PREPROC" "$CHUNKS_SX" <<'PY'
+import os, re, sys
+preproc_path, out_path = sys.argv[1], sys.argv[2]
+max_chunks = int(os.environ.get("MAX_CHUNKS", "590"))
+text = open(preproc_path).read()
+# keep the `}T` attached to the preceding chunk
+parts = re.split(r'(\}T)', text)
+chunks = []
+buf = ""
+for p in parts:
+    buf += p
+    if p == "}T":
+        s = buf.strip()
+        if s:
+            chunks.append(s)
+        buf = ""
+if buf.strip():
+    chunks.append(buf.strip())
+chunks = chunks[:max_chunks]
+
+def esc(s):
+    s = s.replace('\\', '\\\\').replace('"', '\\"')
+    s = s.replace('\r', ' ').replace('\n', ' ')
+    s = re.sub(r'\s+', ' ', s).strip()
+    return s
+
+with open(out_path, "w") as f:
+    f.write("(define hayes-chunks (list\n")
+    for c in chunks:
+        f.write('  "' + esc(c) + '"\n')
+    f.write("))\n\n")
+    f.write("(define\n")
+    f.write("  hayes-run-all\n")
+    f.write("  (fn\n")
+    f.write("    ()\n")
+    f.write("    (hayes-reset!)\n")
+    f.write("    (let ((s (hayes-boot)))\n")
+    f.write("      (for-each (fn (c) (hayes-run-chunk s c)) hayes-chunks))\n")
+    f.write("    (hayes-summary)))\n")
+PY
+
+# 4. run it
+OUT=$(printf '(epoch 1)\n(load "lib/forth/runtime.sx")\n(epoch 2)\n(load "lib/forth/reader.sx")\n(epoch 3)\n(load "lib/forth/interpreter.sx")\n(epoch 4)\n(load "lib/forth/compiler.sx")\n(epoch 5)\n(load "lib/forth/hayes-runner.sx")\n(epoch 6)\n(load "%s")\n(epoch 7)\n(eval "(hayes-run-all)")\n' "$CHUNKS_SX" \
+  | timeout 180 "$SX_SERVER" 2>&1)
+STATUS=$?
+
+SUMMARY=$(printf '%s\n' "$OUT" | awk '/^\{:pass / {print; exit}')
+PASS=$(printf '%s' "$SUMMARY" | sed -n 's/.*:pass \([0-9-]*\).*/\1/p')
+FAIL=$(printf '%s' "$SUMMARY" | sed -n 's/.*:fail \([0-9-]*\).*/\1/p')
+ERR=$(printf '%s' "$SUMMARY" | sed -n 's/.*:error \([0-9-]*\).*/\1/p')
+TOTAL=$(printf '%s' "$SUMMARY" | sed -n 's/.*:total \([0-9-]*\).*/\1/p')
+CHUNK_COUNT=$(grep -c '^  "' "$CHUNKS_SX" || echo 0)
+TOTAL_AVAILABLE=$(grep -c '}T' "$PREPROC" || echo 0)
+
+NOW="$(date -u +%Y-%m-%dT%H:%M:%SZ)"
+
+if [ -z "$PASS" ]; then
+  PASS=0; FAIL=0; ERR=0; TOTAL=0
+  NOTE="runner halted before completing (timeout or SX error)"
+else
+  NOTE="completed"
+fi
+
+PCT=0
+if [ "$TOTAL" -gt 0 ]; then
+  PCT=$((PASS * 100 / TOTAL))
+fi
+
+cat > "$OUT_JSON" <<JSON
+{
+  "source": "gerryjackson/forth2012-test-suite src/core.fr",
+  "generated_at": "$NOW",
+  "chunks_available": $TOTAL_AVAILABLE,
+  "chunks_fed": $CHUNK_COUNT,
+  "total": $TOTAL,
+  "pass": $PASS,
+  "fail": $FAIL,
+  "error": $ERR,
+  "percent": $PCT,
+  "note": "$NOTE"
+}
+JSON
+
+cat > "$OUT_MD" <<MD
+# Forth Hayes Core scoreboard
+
+| metric            | value |
+| ----------------- | ----: |
+| chunks available  | $TOTAL_AVAILABLE |
+| chunks fed        | $CHUNK_COUNT |
+| total             | $TOTAL |
+| pass              | $PASS |
+| fail              | $FAIL |
+| error             | $ERR |
+| percent           | ${PCT}% |
+
+- **Source**: \`gerryjackson/forth2012-test-suite\` \`src/core.fr\`
+- **Generated**: $NOW
+- **Note**: $NOTE
+
+A "chunk" is any preprocessed segment ending at a \`}T\` (every Hayes test
+is one chunk, plus the small declaration blocks between tests).
+The runner catches raised errors at chunk boundaries so one bad chunk
+does not abort the rest. \`error\` covers chunks that raised; \`fail\`
+covers tests whose \`->\` / \`}T\` comparison mismatched.
+
+### Chunk cap
+
+\`conformance.sh\` processes the first \`\$MAX_CHUNKS\` chunks (default
+**638**, i.e. the whole Hayes Core file). Lower the cap temporarily
+while iterating on primitives if a regression re-opens an infinite
+loop in later tests.
+MD
+
+echo "$SUMMARY"
+echo "Scoreboard: $OUT_JSON"
+echo "           $OUT_MD"
+
+if [ "$STATUS" -ne 0 ] && [ "$TOTAL" -eq 0 ]; then
+  exit 1
+fi
--- a/lib/forth/hayes-runner.sx
+++ b/lib/forth/hayes-runner.sx
@@ -0,0 +1,158 @@
+;; Hayes conformance test runner.
+;; Installs T{ -> }T as Forth primitives that snapshot and compare dstack,
+;; plus stub TESTING / HEX / DECIMAL so the Hayes Core file can stream
+;; through the interpreter without halting on unsupported metadata words.
+
+(define hayes-pass 0)
+(define hayes-fail 0)
+(define hayes-error 0)
+(define hayes-start-depth 0)
+(define hayes-actual (list))
+(define hayes-actual-set false)
+(define hayes-failures (list))
+(define hayes-first-error "")
+(define hayes-error-hist (dict))
+
+(define
+  hayes-reset!
+  (fn
+    ()
+    (set! hayes-pass 0)
+    (set! hayes-fail 0)
+    (set! hayes-error 0)
+    (set! hayes-start-depth 0)
+    (set! hayes-actual (list))
+    (set! hayes-actual-set false)
+    (set! hayes-failures (list))
+    (set! hayes-first-error "")
+    (set! hayes-error-hist (dict))))
+
+(define
+  hayes-slice
+  (fn
+    (state base)
+    (let
+      ((n (- (forth-depth state) base)))
+      (if (<= n 0) (list) (take (get state "dstack") n)))))
+
+(define
+  hayes-truncate!
+  (fn
+    (state base)
+    (let
+      ((n (- (forth-depth state) base)))
+      (when (> n 0) (dict-set! state "dstack" (drop (get state "dstack") n))))))
+
+(define
+  hayes-install!
+  (fn
+    (state)
+    (forth-def-prim!
+      state
+      "T{"
+      (fn
+        (s)
+        (set! hayes-start-depth (forth-depth s))
+        (set! hayes-actual-set false)
+        (set! hayes-actual (list))))
+    (forth-def-prim!
+      state
+      "->"
+      (fn
+        (s)
+        (set! hayes-actual (hayes-slice s hayes-start-depth))
+        (set! hayes-actual-set true)
+        (hayes-truncate! s hayes-start-depth)))
+    (forth-def-prim!
+      state
+      "}T"
+      (fn
+        (s)
+        (let
+          ((expected (hayes-slice s hayes-start-depth)))
+          (hayes-truncate! s hayes-start-depth)
+          (if
+            (and hayes-actual-set (= expected hayes-actual))
+            (set! hayes-pass (+ hayes-pass 1))
+            (begin
+              (set! hayes-fail (+ hayes-fail 1))
+              (set!
+                hayes-failures
+                (concat
+                  hayes-failures
+                  (list
+                    (dict
+                      "kind"
+                      "fail"
+                      "expected"
+                      (str expected)
+                      "actual"
+                      (str hayes-actual))))))))))
+    (forth-def-prim! state "TESTING" (fn (s) nil))
+    ;; HEX/DECIMAL are real primitives now (runtime.sx) — no stub needed.
+    state))
+
+(define
+  hayes-boot
+  (fn () (let ((s (forth-boot))) (hayes-install! s) (hayes-reset!) s)))
+
+;; Run a single preprocessed chunk (string of Forth source) on the shared
+;; state. Catch any raised error and move on — the chunk boundary is a
+;; safe resume point.
+(define
+  hayes-bump-error-key!
+  (fn
+    (err)
+    (let
+      ((msg (str err)))
+      (let
+        ((space-idx (index-of msg " ")))
+        (let
+          ((key
+            (if
+              (> space-idx 0)
+              (substr msg 0 space-idx)
+              msg)))
+          (dict-set!
+            hayes-error-hist
+            key
+            (+ 1 (or (get hayes-error-hist key) 0))))))))
+
+(define
+  hayes-run-chunk
+  (fn
+    (state src)
+    (guard
+      (err
+        ((= 1 1)
+          (begin
+            (set! hayes-error (+ hayes-error 1))
+            (when
+              (= (len hayes-first-error) 0)
+              (set! hayes-first-error (str err)))
+            (hayes-bump-error-key! err)
+            (dict-set! state "dstack" (list))
+            (dict-set! state "rstack" (list))
+            (dict-set! state "compiling" false)
+            (dict-set! state "current-def" nil)
+            (dict-set! state "cstack" (list))
+            (dict-set! state "input" (list)))))
+      (forth-interpret state src))))
+
+(define
+  hayes-summary
+  (fn
+    ()
+    (dict
+      "pass"
+      hayes-pass
+      "fail"
+      hayes-fail
+      "error"
+      hayes-error
+      "total"
+      (+ (+ hayes-pass hayes-fail) hayes-error)
+      "first-error"
+      hayes-first-error
+      "error-hist"
+      hayes-error-hist)))
--- a/lib/forth/interpreter.sx
+++ b/lib/forth/interpreter.sx
@@ -5,7 +5,39 @@

 (define
  forth-execute-word
-  (fn (state word) (let ((body (get word "body"))) (body state))))
+  (fn
+    (state word)
+    (dict-set! word "call-count" (+ 1 (or (get word "call-count") 0)))
+    (let ((body (get word "body"))) (body state))))
+
+(define
+  forth-hot-words
+  (fn
+    (state threshold)
+    (forth-hot-walk
+      (keys (get state "dict"))
+      (get state "dict")
+      threshold
+      (list))))
+
+(define
+  forth-hot-walk
+  (fn
+    (names dict threshold acc)
+    (if
+      (= (len names) 0)
+      acc
+      (let
+        ((n (first names)))
+        (let
+          ((w (get dict n)))
+          (let
+            ((c (or (get w "call-count") 0)))
+            (forth-hot-walk
+              (rest names)
+              dict
+              threshold
+              (if (>= c threshold) (cons (list n c) acc) acc))))))))

 (define
  forth-interpret-token
@@ -17,7 +49,7 @@
        (not (nil? w))
        (forth-execute-word state w)
        (let
-          ((n (forth-parse-number tok (get state "base"))))
+          ((n (forth-parse-number tok (get (get state "vars") "base"))))
          (if
            (not (nil? n))
            (forth-push state n)
--- a/lib/forth/runtime.sx
+++ b/lib/forth/runtime.sx
--- a/lib/forth/scoreboard.json
+++ b/lib/forth/scoreboard.json
@@ -0,0 +1,12 @@
+{
+  "source": "gerryjackson/forth2012-test-suite src/core.fr",
+  "generated_at": "2026-05-05T21:30:21Z",
+  "chunks_available": 638,
+  "chunks_fed": 638,
+  "total": 638,
+  "pass": 632,
+  "fail": 6,
+  "error": 0,
+  "percent": 99,
+  "note": "completed"
+}
--- a/lib/forth/scoreboard.md
+++ b/lib/forth/scoreboard.md
@@ -0,0 +1,28 @@
+# Forth Hayes Core scoreboard
+
+| metric            | value |
+| ----------------- | ----: |
+| chunks available  | 638 |
+| chunks fed        | 638 |
+| total             | 638 |
+| pass              | 632 |
+| fail              | 6 |
+| error             | 0 |
+| percent           | 99% |
+
+- **Source**: `gerryjackson/forth2012-test-suite` `src/core.fr`
+- **Generated**: 2026-05-05T21:30:21Z
+- **Note**: completed
+
+A "chunk" is any preprocessed segment ending at a `}T` (every Hayes test
+is one chunk, plus the small declaration blocks between tests).
+The runner catches raised errors at chunk boundaries so one bad chunk
+does not abort the rest. `error` covers chunks that raised; `fail`
+covers tests whose `->` / `}T` comparison mismatched.
+
+### Chunk cap
+
+`conformance.sh` processes the first `$MAX_CHUNKS` chunks (default
+**638**, i.e. the whole Hayes Core file). Lower the cap temporarily
+while iterating on primitives if a regression re-opens an infinite
+loop in later tests.
--- a/lib/forth/tests/test-phase3.sx
+++ b/lib/forth/tests/test-phase3.sx
@@ -0,0 +1,239 @@
+;; Phase 3 — control flow (IF/ELSE/THEN, BEGIN/UNTIL/WHILE/REPEAT/AGAIN,
+;; DO/LOOP, return stack). Grows as each control construct lands.
+
+(define forth-p3-passed 0)
+(define forth-p3-failed 0)
+(define forth-p3-failures (list))
+
+(define
+  forth-p3-assert
+  (fn
+    (label expected actual)
+    (if
+      (= expected actual)
+      (set! forth-p3-passed (+ forth-p3-passed 1))
+      (begin
+        (set! forth-p3-failed (+ forth-p3-failed 1))
+        (set!
+          forth-p3-failures
+          (concat
+            forth-p3-failures
+            (list
+              (str label ": expected " (str expected) " got " (str actual)))))))))
+
+(define
+  forth-p3-check-stack
+  (fn
+    (label src expected)
+    (let ((r (forth-run src))) (forth-p3-assert label expected (nth r 2)))))
+
+(define
+  forth-p3-if-tests
+  (fn
+    ()
+    (forth-p3-check-stack
+      "IF taken (-1)"
+      ": Q -1 IF 10 THEN ; Q"
+      (list 10))
+    (forth-p3-check-stack
+      "IF not taken (0)"
+      ": Q 0 IF 10 THEN ; Q"
+      (list))
+    (forth-p3-check-stack
+      "IF with non-zero truthy"
+      ": Q 42 IF 10 THEN ; Q"
+      (list 10))
+    (forth-p3-check-stack
+      "IF ELSE — true branch"
+      ": Q -1 IF 10 ELSE 20 THEN ; Q"
+      (list 10))
+    (forth-p3-check-stack
+      "IF ELSE — false branch"
+      ": Q 0 IF 10 ELSE 20 THEN ; Q"
+      (list 20))
+    (forth-p3-check-stack
+      "IF consumes flag"
+      ": Q IF 1 ELSE 2 THEN ; 0 Q"
+      (list 2))
+    (forth-p3-check-stack
+      "absolute value via IF"
+      ": ABS2 DUP 0 < IF NEGATE THEN ; -7 ABS2"
+      (list 7))
+    (forth-p3-check-stack
+      "abs leaves positive alone"
+      ": ABS2 DUP 0 < IF NEGATE THEN ; 7 ABS2"
+      (list 7))
+    (forth-p3-check-stack
+      "sign: negative"
+      ": SIGN DUP 0 < IF DROP -1 ELSE DROP 1 THEN ; -3 SIGN"
+      (list -1))
+    (forth-p3-check-stack
+      "sign: positive"
+      ": SIGN DUP 0 < IF DROP -1 ELSE DROP 1 THEN ; 3 SIGN"
+      (list 1))
+    (forth-p3-check-stack
+      "nested IF (both true)"
+      ": Q 1 IF 1 IF 10 ELSE 20 THEN ELSE 30 THEN ; Q"
+      (list 10))
+    (forth-p3-check-stack
+      "nested IF (inner false)"
+      ": Q 1 IF 0 IF 10 ELSE 20 THEN ELSE 30 THEN ; Q"
+      (list 20))
+    (forth-p3-check-stack
+      "nested IF (outer false)"
+      ": Q 0 IF 0 IF 10 ELSE 20 THEN ELSE 30 THEN ; Q"
+      (list 30))
+    (forth-p3-check-stack
+      "IF before other ops"
+      ": Q 1 IF 5 ELSE 6 THEN 2 * ; Q"
+      (list 10))
+    (forth-p3-check-stack
+      "IF in chained def"
+      ": POS? 0 > ;
+       : DOUBLE-IF-POS DUP POS? IF 2 * THEN ;
+       3 DOUBLE-IF-POS"
+      (list 6))
+    (forth-p3-check-stack
+      "empty then branch"
+      ": Q 1 IF THEN 99 ; Q"
+      (list 99))
+    (forth-p3-check-stack
+      "empty else branch"
+      ": Q 0 IF 99 ELSE THEN ; Q"
+      (list))
+    (forth-p3-check-stack
+      "sequential IF blocks"
+      ": Q -1 IF 1 THEN -1 IF 2 THEN ; Q"
+      (list 1 2))))
+
+(define
+  forth-p3-loop-tests
+  (fn
+    ()
+    (forth-p3-check-stack
+      "BEGIN UNTIL (countdown to zero)"
+      ": CD BEGIN 1- DUP 0 = UNTIL ; 3 CD"
+      (list 0))
+    (forth-p3-check-stack
+      "BEGIN UNTIL — single pass (UNTIL true immediately)"
+      ": Q BEGIN -1 UNTIL 42 ; Q"
+      (list 42))
+    (forth-p3-check-stack
+      "BEGIN UNTIL — accumulate sum 1+2+3"
+      ": SUM3 0 3 BEGIN TUCK + SWAP 1- DUP 0 = UNTIL DROP ; SUM3"
+      (list 6))
+    (forth-p3-check-stack
+      "BEGIN WHILE REPEAT — triangular sum 5"
+      ": TRI 0 5 BEGIN DUP 0 > WHILE TUCK + SWAP 1- REPEAT DROP ; TRI"
+      (list 15))
+    (forth-p3-check-stack
+      "BEGIN WHILE REPEAT — zero iterations"
+      ": TRI 0 0 BEGIN DUP 0 > WHILE TUCK + SWAP 1- REPEAT DROP ; TRI"
+      (list 0))
+    (forth-p3-check-stack
+      "BEGIN WHILE REPEAT — one iteration"
+      ": TRI 0 1 BEGIN DUP 0 > WHILE TUCK + SWAP 1- REPEAT DROP ; TRI"
+      (list 1))
+    (forth-p3-check-stack
+      "nested BEGIN UNTIL"
+      ": INNER BEGIN 1- DUP 0 = UNTIL DROP ;
+       : OUTER BEGIN 3 INNER 1- DUP 0 = UNTIL ;
+       2 OUTER"
+      (list 0))
+    (forth-p3-check-stack
+      "BEGIN UNTIL after colon prefix"
+      ": TEN 10 ;
+       : CD TEN BEGIN 1- DUP 0 = UNTIL ;
+       CD"
+      (list 0))
+    (forth-p3-check-stack
+      "WHILE inside IF branch"
+      ": Q 1 IF 0 3 BEGIN DUP 0 > WHILE TUCK + SWAP 1- REPEAT DROP ELSE 99 THEN ; Q"
+      (list 6))))
+
+(define
+  forth-p3-do-tests
+  (fn
+    ()
+    (forth-p3-check-stack
+      "DO LOOP — simple sum 0..4"
+      ": SUM 0 5 0 DO I + LOOP ; SUM"
+      (list 10))
+    (forth-p3-check-stack
+      "DO LOOP — 10..14 sum using I"
+      ": SUM 0 15 10 DO I + LOOP ; SUM"
+      (list 60))
+    (forth-p3-check-stack
+      "DO LOOP — limit = start runs one pass"
+      ": SUM 0 5 5 DO I + LOOP ; SUM"
+      (list 5))
+    (forth-p3-check-stack
+      "DO LOOP — count iterations"
+      ": COUNT 0 4 0 DO 1+ LOOP ; COUNT"
+      (list 4))
+    (forth-p3-check-stack
+      "DO LOOP — nested, I inner / J outer"
+      ": MATRIX 0 3 0 DO 3 0 DO I J + + LOOP LOOP ; MATRIX"
+      (list 18))
+    (forth-p3-check-stack
+      "DO LOOP — I used in arithmetic"
+      ": DBL 0 5 1 DO I 2 * + LOOP ; DBL"
+      (list 20))
+    (forth-p3-check-stack
+      "+LOOP — count by 2"
+      ": Q 0 10 0 DO I + 2 +LOOP ; Q"
+      (list 20))
+    (forth-p3-check-stack
+      "+LOOP — count by 3"
+      ": Q 0 10 0 DO I + 3 +LOOP ; Q"
+      (list 18))
+    (forth-p3-check-stack
+      "+LOOP — negative step"
+      ": Q 0 0 10 DO I + -1 +LOOP ; Q"
+      (list 55))
+    (forth-p3-check-stack
+      "LEAVE — early exit at I=3"
+      ": Q 0 10 0 DO I 3 = IF LEAVE THEN I + LOOP ; Q"
+      (list 3))
+    (forth-p3-check-stack
+      "LEAVE — in nested loop exits only inner"
+      ": Q 0 3 0 DO 5 0 DO I 2 = IF LEAVE THEN I + LOOP LOOP ; Q"
+      (list 3))
+    (forth-p3-check-stack
+      "DO LOOP preserves outer stack"
+      ": Q 99 5 0 DO I + LOOP ; Q"
+      (list 109))
+    (forth-p3-check-stack
+      ">R R>"
+      ": Q 7 >R 11 R> ; Q"
+      (list 11 7))
+    (forth-p3-check-stack
+      ">R R@ R>"
+      ": Q 7 >R R@ R> ; Q"
+      (list 7 7))
+    (forth-p3-check-stack
+      "2>R 2R>"
+      ": Q 1 2 2>R 99 2R> ; Q"
+      (list 99 1 2))
+    (forth-p3-check-stack
+      "2>R 2R@ 2R>"
+      ": Q 3 4 2>R 2R@ 2R> ; Q"
+      (list 3 4 3 4))))
+
+(define
+  forth-p3-run-all
+  (fn
+    ()
+    (set! forth-p3-passed 0)
+    (set! forth-p3-failed 0)
+    (set! forth-p3-failures (list))
+    (forth-p3-if-tests)
+    (forth-p3-loop-tests)
+    (forth-p3-do-tests)
+    (dict
+      "passed"
+      forth-p3-passed
+      "failed"
+      forth-p3-failed
+      "failures"
+      forth-p3-failures)))
--- a/lib/forth/tests/test-phase4.sx
+++ b/lib/forth/tests/test-phase4.sx
@@ -0,0 +1,268 @@
+;; Phase 4 — strings + more Core.
+;; Uses the byte-memory model on state ("mem" dict + "here" cursor).
+
+(define forth-p4-passed 0)
+(define forth-p4-failed 0)
+(define forth-p4-failures (list))
+
+(define
+  forth-p4-assert
+  (fn
+    (label expected actual)
+    (if
+      (= expected actual)
+      (set! forth-p4-passed (+ forth-p4-passed 1))
+      (begin
+        (set! forth-p4-failed (+ forth-p4-failed 1))
+        (set!
+          forth-p4-failures
+          (concat
+            forth-p4-failures
+            (list
+              (str label ": expected " (str expected) " got " (str actual)))))))))
+
+(define
+  forth-p4-check-output
+  (fn
+    (label src expected)
+    (let ((r (forth-run src))) (forth-p4-assert label expected (nth r 1)))))
+
+(define
+  forth-p4-check-stack-size
+  (fn
+    (label src expected-n)
+    (let
+      ((r (forth-run src)))
+      (forth-p4-assert label expected-n (len (nth r 2))))))
+
+(define
+  forth-p4-check-top
+  (fn
+    (label src expected)
+    (let
+      ((r (forth-run src)))
+      (let
+        ((stk (nth r 2)))
+        (forth-p4-assert label expected (nth stk (- (len stk) 1)))))))
+
+(define
+  forth-p4-check-typed
+  (fn
+    (label src expected)
+    (forth-p4-check-output label (str src " TYPE") expected)))
+
+(define
+  forth-p4-string-tests
+  (fn
+    ()
+    (forth-p4-check-typed
+      "S\" + TYPE — hello"
+      "S\" HELLO\""
+      "HELLO")
+    (forth-p4-check-typed
+      "S\" + TYPE — two words"
+      "S\" HELLO WORLD\""
+      "HELLO WORLD")
+    (forth-p4-check-typed
+      "S\" + TYPE — empty"
+      "S\" \""
+      "")
+    (forth-p4-check-typed
+      "S\" + TYPE — single char"
+      "S\" X\""
+      "X")
+    (forth-p4-check-stack-size
+      "S\" pushes (addr len)"
+      "S\" HI\""
+      2)
+    (forth-p4-check-top
+      "S\" length is correct"
+      "S\" HELLO\""
+      5)
+    (forth-p4-check-output
+      ".\" prints at interpret time"
+      ".\" HELLO\""
+      "HELLO")
+    (forth-p4-check-output
+      ".\" in colon def"
+      ": GREET .\" HI \" ; GREET GREET"
+      "HI HI ")))
+
+(define
+  forth-p4-count-tests
+  (fn
+    ()
+    (forth-p4-check-typed
+      "C\" + COUNT + TYPE"
+      "C\" ABC\" COUNT"
+      "ABC")
+    (forth-p4-check-typed
+      "C\" then COUNT leaves right len"
+      "C\" HI THERE\" COUNT"
+      "HI THERE")))
+
+(define
+  forth-p4-fill-tests
+  (fn
+    ()
+    (forth-p4-check-typed
+      "FILL overwrites prefix bytes"
+      "S\" ABCDE\" 2DUP DROP 3 65 FILL"
+      "AAADE")
+    (forth-p4-check-typed
+      "BLANK sets spaces"
+      "S\" XYZAB\" 2DUP DROP 3 BLANK"
+      "   AB")))
+
+(define
+  forth-p4-cmove-tests
+  (fn
+    ()
+    (forth-p4-check-output
+      "CMOVE copies HELLO forward"
+      ": MKH 72 0 C! 69 1 C! 76 2 C! 76 3 C! 79 4 C! ;
+       : T MKH 0 10 5 CMOVE 10 5 TYPE ; T"
+      "HELLO")
+    (forth-p4-check-output
+      "CMOVE> copies overlapping backward"
+      ": MKA 65 0 C! 66 1 C! 67 2 C! ;
+       : T MKA 0 1 2 CMOVE> 0 3 TYPE ; T"
+      "AAB")
+    (forth-p4-check-output
+      "MOVE picks direction for overlap"
+      ": MKA 65 0 C! 66 1 C! 67 2 C! ;
+       : T MKA 0 1 2 MOVE 0 3 TYPE ; T"
+      "AAB")))
+
+(define
+  forth-p4-charplus-tests
+  (fn
+    ()
+    (forth-p4-check-top
+      "CHAR+ increments"
+      "5 CHAR+"
+      6)))
+
+(define
+  forth-p4-char-tests
+  (fn
+    ()
+    (forth-p4-check-top "CHAR A -> 65" "CHAR A" 65)
+    (forth-p4-check-top "CHAR x -> 120" "CHAR x" 120)
+    (forth-p4-check-top "CHAR takes only first char" "CHAR HELLO" 72)
+    (forth-p4-check-top
+      "[CHAR] compiles literal"
+      ": AA [CHAR] A ; AA"
+      65)
+    (forth-p4-check-top
+      "[CHAR] reads past IMMEDIATE"
+      ": ZZ [CHAR] Z ; ZZ"
+      90)
+    (forth-p4-check-stack-size
+      "[CHAR] doesn't leak at compile time"
+      ": FOO [CHAR] A ; "
+      0)))
+
+(define
+  forth-p4-key-accept-tests
+  (fn
+    ()
+    (let
+      ((r (forth-run "1000 2 ACCEPT")))
+      (let ((stk (nth r 2))) (forth-p4-assert "ACCEPT empty buf -> 0" (list 0) stk)))))
+
+(define
+  forth-p4-shift-tests
+  (fn
+    ()
+    (forth-p4-check-top "1 0 LSHIFT" "1 0 LSHIFT" 1)
+    (forth-p4-check-top "1 1 LSHIFT" "1 1 LSHIFT" 2)
+    (forth-p4-check-top "1 2 LSHIFT" "1 2 LSHIFT" 4)
+    (forth-p4-check-top "1 15 LSHIFT" "1 15 LSHIFT" 32768)
+    (forth-p4-check-top "1 31 LSHIFT" "1 31 LSHIFT" -2147483648)
+    (forth-p4-check-top "1 0 RSHIFT" "1 0 RSHIFT" 1)
+    (forth-p4-check-top "1 1 RSHIFT" "1 1 RSHIFT" 0)
+    (forth-p4-check-top "2 1 RSHIFT" "2 1 RSHIFT" 1)
+    (forth-p4-check-top "4 2 RSHIFT" "4 2 RSHIFT" 1)
+    (forth-p4-check-top "-1 1 RSHIFT (logical, not arithmetic)" "-1 1 RSHIFT" 2147483647)
+    (forth-p4-check-top "MSB via 1S 1 RSHIFT INVERT" "0 INVERT 1 RSHIFT INVERT" -2147483648)))
+
+(define
+  forth-p4-sp-tests
+  (fn
+    ()
+    (forth-p4-check-top "SP@ returns depth (0)" "SP@" 0)
+    (forth-p4-check-top
+      "SP@ after pushes"
+      "1 2 3 SP@ SWAP DROP SWAP DROP SWAP DROP"
+      3)
+    (forth-p4-check-stack-size
+      "SP! truncates"
+      "1 2 3 4 5 2 SP!"
+      2)
+    (forth-p4-check-top
+      "SP! leaves base items intact"
+      "1 2 3 4 5 2 SP!"
+      2)))
+
+(define
+  forth-p4-base-tests
+  (fn
+    ()
+    (forth-p4-check-top
+      "BASE default is 10"
+      "BASE @"
+      10)
+    (forth-p4-check-top
+      "HEX switches base to 16"
+      "HEX BASE @"
+      16)
+    (forth-p4-check-top
+      "DECIMAL resets to 10"
+      "HEX DECIMAL BASE @"
+      10)
+    (forth-p4-check-top
+      "HEX parses 10 as 16"
+      "HEX 10"
+      16)
+    (forth-p4-check-top
+      "HEX parses FF as 255"
+      "HEX FF"
+      255)
+    (forth-p4-check-top
+      "DECIMAL parses 10 as 10"
+      "HEX DECIMAL 10"
+      10)
+    (forth-p4-check-top
+      "OCTAL parses 17 as 15"
+      "OCTAL 17"
+      15)
+    (forth-p4-check-top
+      "BASE @ ; 16 BASE ! ; BASE @"
+      "BASE @ 16 BASE ! BASE @ SWAP DROP"
+      16)))
+
+(define
+  forth-p4-run-all
+  (fn
+    ()
+    (set! forth-p4-passed 0)
+    (set! forth-p4-failed 0)
+    (set! forth-p4-failures (list))
+    (forth-p4-string-tests)
+    (forth-p4-count-tests)
+    (forth-p4-fill-tests)
+    (forth-p4-cmove-tests)
+    (forth-p4-charplus-tests)
+    (forth-p4-char-tests)
+    (forth-p4-key-accept-tests)
+    (forth-p4-base-tests)
+    (forth-p4-shift-tests)
+    (forth-p4-sp-tests)
+    (dict
+      "passed"
+      forth-p4-passed
+      "failed"
+      forth-p4-failed
+      "failures"
+      forth-p4-failures)))
--- a/lib/forth/tests/test-phase5.sx
+++ b/lib/forth/tests/test-phase5.sx
@@ -0,0 +1,333 @@
+;; Phase 5 — Core Extension + memory primitives.
+
+(define forth-p5-passed 0)
+(define forth-p5-failed 0)
+(define forth-p5-failures (list))
+
+(define
+  forth-p5-assert
+  (fn
+    (label expected actual)
+    (if
+      (= expected actual)
+      (set! forth-p5-passed (+ forth-p5-passed 1))
+      (begin
+        (set! forth-p5-failed (+ forth-p5-failed 1))
+        (set!
+          forth-p5-failures
+          (concat
+            forth-p5-failures
+            (list
+              (str label ": expected " (str expected) " got " (str actual)))))))))
+
+(define
+  forth-p5-check-stack
+  (fn
+    (label src expected)
+    (let ((r (forth-run src))) (forth-p5-assert label expected (nth r 2)))))
+
+(define
+  forth-p5-check-top
+  (fn
+    (label src expected)
+    (let
+      ((r (forth-run src)))
+      (let
+        ((stk (nth r 2)))
+        (forth-p5-assert label expected (nth stk (- (len stk) 1)))))))
+
+(define
+  forth-p5-create-tests
+  (fn
+    ()
+    (forth-p5-check-top
+      "CREATE pushes HERE-at-creation"
+      "HERE CREATE FOO FOO ="
+      -1)
+    (forth-p5-check-top
+      "CREATE + ALLOT advances HERE"
+      "HERE 5 ALLOT HERE SWAP -"
+      5)
+    (forth-p5-check-top
+      "CREATE + , stores cell"
+      "CREATE FOO 42 , FOO @"
+      42)
+    (forth-p5-check-stack
+      "CREATE multiple ,"
+      "CREATE TBL 1 , 2 , 3 , TBL @ TBL CELL+ @ TBL CELL+ CELL+ @"
+      (list 1 2 3))
+    (forth-p5-check-top
+      "C, stores byte"
+      "CREATE B 65 C, 66 C, B C@"
+      65)))
+
+(define
+  forth-p5-unsigned-tests
+  (fn
+    ()
+    (forth-p5-check-top "1 2 U<" "1 2 U<" -1)
+    (forth-p5-check-top "2 1 U<" "2 1 U<" 0)
+    (forth-p5-check-top "0 1 U<" "0 1 U<" -1)
+    (forth-p5-check-top "-1 1 U< (since -1 unsigned is huge)" "-1 1 U<" 0)
+    (forth-p5-check-top "1 -1 U<" "1 -1 U<" -1)
+    (forth-p5-check-top "1 2 U>" "1 2 U>" 0)
+    (forth-p5-check-top "-1 1 U>" "-1 1 U>" -1)))
+
+(define
+  forth-p5-2bang-tests
+  (fn
+    ()
+    (forth-p5-check-stack
+      "2! / 2@"
+      "CREATE X 0 , 0 , 11 22 X 2! X 2@"
+      (list 11 22))))
+
+(define
+  forth-p5-mixed-tests
+  (fn
+    ()
+    (forth-p5-check-stack "S>D positive" "5 S>D" (list 5 0))
+    (forth-p5-check-stack "S>D negative" "-5 S>D" (list -5 -1))
+    (forth-p5-check-stack "S>D zero" "0 S>D" (list 0 0))
+    (forth-p5-check-top "D>S keeps low" "5 0 D>S" 5)
+    (forth-p5-check-stack "M* small positive" "3 4 M*" (list 12 0))
+    (forth-p5-check-stack "M* negative" "-3 4 M*" (list -12 -1))
+    (forth-p5-check-stack
+      "M* negative * negative"
+      "-3 -4 M*"
+      (list 12 0))
+    (forth-p5-check-stack "UM* small" "3 4 UM*" (list 12 0))
+    (forth-p5-check-stack
+      "UM/MOD: 100 0 / 5"
+      "100 0 5 UM/MOD"
+      (list 0 20))
+    (forth-p5-check-stack
+      "FM/MOD: -7 / 2 floored"
+      "-7 -1 2 FM/MOD"
+      (list 1 -4))
+    (forth-p5-check-stack
+      "SM/REM: -7 / 2 truncated"
+      "-7 -1 2 SM/REM"
+      (list -1 -3))
+    (forth-p5-check-top "*/ truncated" "7 11 13 */" 5)
+    (forth-p5-check-stack "*/MOD" "7 11 13 */MOD" (list 12 5))))
+
+(define
+  forth-p5-double-tests
+  (fn
+    ()
+    (forth-p5-check-stack "D+ small" "5 0 7 0 D+" (list 12 0))
+    (forth-p5-check-stack "D+ negative" "-5 -1 -3 -1 D+" (list -8 -1))
+    (forth-p5-check-stack "D- small" "10 0 3 0 D-" (list 7 0))
+    (forth-p5-check-stack "DNEGATE positive" "5 0 DNEGATE" (list -5 -1))
+    (forth-p5-check-stack "DNEGATE negative" "-5 -1 DNEGATE" (list 5 0))
+    (forth-p5-check-stack "DABS negative" "-7 -1 DABS" (list 7 0))
+    (forth-p5-check-stack "DABS positive" "7 0 DABS" (list 7 0))
+    (forth-p5-check-top "D= equal" "5 0 5 0 D=" -1)
+    (forth-p5-check-top "D= unequal lo" "5 0 7 0 D=" 0)
+    (forth-p5-check-top "D= unequal hi" "5 0 5 1 D=" 0)
+    (forth-p5-check-top "D< lt" "5 0 7 0 D<" -1)
+    (forth-p5-check-top "D< gt" "7 0 5 0 D<" 0)
+    (forth-p5-check-top "D0= zero" "0 0 D0=" -1)
+    (forth-p5-check-top "D0= nonzero" "5 0 D0=" 0)
+    (forth-p5-check-top "D0< neg" "-5 -1 D0<" -1)
+    (forth-p5-check-top "D0< pos" "5 0 D0<" 0)
+    (forth-p5-check-stack "DMAX" "5 0 7 0 DMAX" (list 7 0))
+    (forth-p5-check-stack "DMIN" "5 0 7 0 DMIN" (list 5 0))))
+
+(define
+  forth-p5-format-tests
+  (fn
+    ()
+    (forth-p4-check-output-passthrough
+      "U. prints with trailing space"
+      "123 U."
+      "123 ")
+    (forth-p4-check-output-passthrough
+      "<# #S #> TYPE — decimal"
+      "123 0 <# #S #> TYPE"
+      "123")
+    (forth-p4-check-output-passthrough
+      "<# #S #> TYPE — hex"
+      "255 HEX 0 <# #S #> TYPE"
+      "FF")
+    (forth-p4-check-output-passthrough
+      "<# # # #> partial"
+      "1234 0 <# # # #> TYPE"
+      "34")
+    (forth-p4-check-output-passthrough
+      "SIGN holds minus"
+      "<# -1 SIGN -1 SIGN 0 0 #> TYPE"
+      "--")
+    (forth-p4-check-output-passthrough
+      ".R right-justifies"
+      "42 5 .R"
+      "   42")
+    (forth-p4-check-output-passthrough
+      ".R negative"
+      "-42 5 .R"
+      "  -42")
+    (forth-p4-check-output-passthrough
+      "U.R"
+      "42 5 U.R"
+      "   42")
+    (forth-p4-check-output-passthrough
+      "HOLD char"
+      "<# 0 0 65 HOLD #> TYPE"
+      "A")))
+
+(define
+  forth-p5-dict-tests
+  (fn
+    ()
+    (forth-p5-check-top
+      "EXECUTE via tick"
+      ": INC 1+ ; 9 ' INC EXECUTE"
+      10)
+    (forth-p5-check-top
+      "['] inside def"
+      ": DUB 2* ; : APPLY ['] DUB EXECUTE ; 5 APPLY"
+      10)
+    (forth-p5-check-top
+      ">BODY of CREATE word"
+      "CREATE C 99 , ' C >BODY @"
+      99)
+    (forth-p5-check-stack
+      "WORD parses next token to counted-string"
+      ": A 5 ; BL WORD A COUNT TYPE"
+      (list))
+    (forth-p5-check-top
+      "FIND on known word -> non-zero"
+      ": A 5 ; BL WORD A FIND SWAP DROP"
+      -1)))
+
+(define
+  forth-p5-state-tests
+  (fn
+    ()
+    (forth-p5-check-top
+      "STATE @ in interpret mode"
+      "STATE @"
+      0)
+    (forth-p5-check-top
+      "STATE @ via IMMEDIATE inside compile"
+      ": GT8 STATE @ ; IMMEDIATE : T GT8 LITERAL ; T"
+      -1)
+    (forth-p5-check-top
+      "[ ] LITERAL captures"
+      ": SEVEN [ 7 ] LITERAL ; SEVEN"
+      7)
+    (forth-p5-check-top
+      "EVALUATE in interpret mode"
+      "S\" 5 7 +\" EVALUATE"
+      12)
+    (forth-p5-check-top
+      "EVALUATE inside def"
+      ": A 100 ; : B S\" A\" EVALUATE ; B"
+      100)))
+
+(define
+  forth-p5-misc-tests
+  (fn
+    ()
+    (forth-p5-check-top "WITHIN inclusive lower" "3 2 10 WITHIN" -1)
+    (forth-p5-check-top "WITHIN exclusive upper" "10 2 10 WITHIN" 0)
+    (forth-p5-check-top "WITHIN below range" "1 2 10 WITHIN" 0)
+    (forth-p5-check-top "WITHIN at lower" "2 2 10 WITHIN" -1)
+    (forth-p5-check-top
+      "EXIT leaves colon-def early"
+      ": F 5 EXIT 99 ; F"
+      5)
+    (forth-p5-check-stack
+      "EXIT in IF branch"
+      ": F 5 0 IF DROP 99 EXIT THEN ; F"
+      (list 5))
+    (forth-p5-check-top
+      "UNLOOP + EXIT in DO"
+      ": SUM 0 10 0 DO I 5 = IF I UNLOOP EXIT THEN LOOP ; SUM"
+      5)))
+
+(define
+  forth-p5-fa-tests
+  (fn
+    ()
+    (forth-p5-check-top
+      "R/O R/W W/O constants"
+      "R/O R/W W/O + +"
+      3)
+    (forth-p5-check-top
+      "CREATE-FILE returns ior=0"
+      "CREATE PAD 50 ALLOT PAD S\" /tmp/test.fxf\" ROT SWAP CMOVE S\" /tmp/test.fxf\" R/W CREATE-FILE SWAP DROP"
+      0)
+    (forth-p5-check-top
+      "WRITE-FILE then CLOSE"
+      "S\" /tmp/t2.fxf\" R/W CREATE-FILE DROP >R S\" HI\" R@ WRITE-FILE R> CLOSE-FILE +"
+      0)
+    (forth-p5-check-top
+      "OPEN-FILE on unknown path returns ior!=0"
+      "S\" /tmp/nope.fxf\" R/O OPEN-FILE SWAP DROP 0 ="
+      0)))
+
+(define
+  forth-p5-string-tests
+  (fn
+    ()
+    (forth-p5-check-top "COMPARE equal" "S\" ABC\" S\" ABC\" COMPARE" 0)
+    (forth-p5-check-top "COMPARE less" "S\" ABC\" S\" ABD\" COMPARE" -1)
+    (forth-p5-check-top "COMPARE greater" "S\" ABD\" S\" ABC\" COMPARE" 1)
+    (forth-p5-check-top
+      "COMPARE prefix less"
+      "S\" AB\" S\" ABC\" COMPARE"
+      -1)
+    (forth-p5-check-top
+      "COMPARE prefix greater"
+      "S\" ABC\" S\" AB\" COMPARE"
+      1)
+    (forth-p5-check-top
+      "SEARCH found flag"
+      "S\" HELLO WORLD\" S\" WORLD\" SEARCH"
+      -1)
+    (forth-p5-check-top
+      "SEARCH not found flag"
+      "S\" HELLO\" S\" XYZ\" SEARCH"
+      0)
+    (forth-p5-check-top
+      "SEARCH empty needle flag"
+      "S\" HELLO\" S\" \" SEARCH"
+      -1)
+    (forth-p5-check-top
+      "SLITERAL via [ S\" ... \" ]"
+      ": A [ S\" HI\" ] SLITERAL ; A SWAP DROP"
+      2)))
+
+(define
+  forth-p4-check-output-passthrough
+  (fn
+    (label src expected)
+    (let ((r (forth-run src))) (forth-p5-assert label expected (nth r 1)))))
+
+(define
+  forth-p5-run-all
+  (fn
+    ()
+    (set! forth-p5-passed 0)
+    (set! forth-p5-failed 0)
+    (set! forth-p5-failures (list))
+    (forth-p5-create-tests)
+    (forth-p5-unsigned-tests)
+    (forth-p5-2bang-tests)
+    (forth-p5-mixed-tests)
+    (forth-p5-double-tests)
+    (forth-p5-format-tests)
+    (forth-p5-dict-tests)
+    (forth-p5-state-tests)
+    (forth-p5-misc-tests)
+    (forth-p5-fa-tests)
+    (forth-p5-string-tests)
+    (dict
+      "passed"
+      forth-p5-passed
+      "failed"
+      forth-p5-failed
+      "failures"
+      forth-p5-failures)))