Stage S-1c: WORD's buffer is per VM; input buffers allotted at VM init, below all compiled code (FABRIC-3.9.0 §8.1)

- The static word_scratch_addr shared by every VM is gone: WORD builds in
  vm->word_buf (257 bytes: count + 255 + NUL). A token over 255 chars is
  refused whole (delimiter restored, >IN unconsumed, vm->error), logged at
  LOG_ERROR and counted -- no more silent cut to 62 chars.
- Pre-existing corruption found by the probe: TIB/>IN/SPAN (and WORD's
  scratch) were allotted lazily at HERE; POST's restore_dict_state(),
  FORGET and COLD rolled HERE below them and compiled the dictionary over
  them (Hera's TIB lay under ACL-RECHECK's body; QUERY/WORD wrote into
  code). Per Captain Bob, all four are now allotted first in both
  vm_init()s (offsets 0-1305); COLD's clamp never goes below them.

Probe (reverted), identical on amd64/aarch64/riscv64: 0 colon bodies inside
the buffers; per-VM isolation; 62/100/255-char tokens full length; 300
refused and counted; interpreter sane after full-width TIB writes.
3-ISA acceptance passes; M7.1a hash and dict_hash set unchanged (here
0xd8 -> 0x5f8).

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

src/starkernel/vm/vm_bootstrap.c

@@ -52,6 +52,7 @@
 #include "../include/rolling_window_of_truth.h"
 #include "../include/dictionary_heat_optimization.h"
 #include "../include/ssm_jacquard.h"
+#include "../include/vm_api.h" /* vm_input_ensure() -- S-1c */
 #include "word_source/include/vocabulary_words.h"
 #include "vm_internal.h"
 #ifdef __STARKERNEL__
@@ -209,6 +210,20 @@ void vm_init_with_host(VM* vm, const VMHostServices *host)
 
     log_message(LOG_DEBUG, "vm_init: memory=%p here=%zu", (void*)vm->memory, vm->here);
 
+    /* FABRIC-3.9.8 Stage S-1c (Captain Bob, 2026-09-24: "allot at VM init"):
+     * the input buffers -- TIB, >IN, SPAN and WORD's buffer -- are allotted
+     * first, at HERE = 0, before POST, capsules or any definition. They used
+     * to be allotted lazily wherever HERE stood; POST's restore_dict_state(),
+     * FORGET and COLD then rolled HERE back below them and compiled the
+     * dictionary over them (Hera's TIB sat under ACL-RECHECK's body). No
+     * HERE rollback can reach below them now. */
+    if (vm_input_ensure(vm) != 0)
+    {
+        log_message(LOG_ERROR, "vm_init: input buffers could not be allotted");
+        vm->error = 1;
+        return;
+    }
+
     vm_bootstrap_scr(vm);
 
     /* STATE (0=interpret, -1=compile) */

src/vm_api.c

@@ -142,6 +142,18 @@ int vm_input_ensure(VM *vm) {
         }
         *vm->span_var = 0;
     }
+    if (!vm->word_buf) {
+        /* S-1c: WORD's buffer, per VM, in this VM's own space, placed with
+         * the other input buffers -- never mid-dictionary, never inside a
+         * definition being compiled. After SPAN so TIB/>IN/SPAN keep their
+         * addresses. */
+        vm->word_buf = (unsigned char *) vm_allot(vm, WORD_BUFFER_SIZE);
+        if (!vm->word_buf) {
+            vm->error = 1;
+            return 1;
+        }
+        memset(vm->word_buf, 0, WORD_BUFFER_SIZE);
+    }
     return 0;
 }
 

src/vm_bootstrap.c

@@ -62,6 +62,7 @@
 #include "../include/dictionary_heat_optimization.h"
 #include "../include/ssm_jacquard.h"
 #include "../include/platform_alloc.h"
+#include "../include/vm_api.h" /* vm_input_ensure() -- S-1c */
 #include "word_source/include/vocabulary_words.h"
 
 #ifdef __STARKERNEL__
@@ -245,6 +246,17 @@ void vm_init(VM* vm)
         memset(p, 0, 64);
     }
 
+    /* FABRIC-3.9.8 Stage S-1c: the input buffers (TIB, >IN, SPAN, WORD's
+     * buffer) are allotted here, before any definition, so no HERE rollback
+     * (test harness restore, FORGET, COLD) can reach below them. Same as the
+     * kernel's vm_init(). */
+    if (vm_input_ensure(vm) != 0)
+    {
+        vm->error = 1;
+        log_message(LOG_ERROR, "vm_init: input buffers could not be allotted");
+        return;
+    }
+
     vm_bootstrap_scr(vm);
 
     vm->mode = MODE_INTERPRET;

src/word_source/include/string_words.h

@@ -149,4 +149,7 @@
  */
 void register_string_words(VM * vm);
 
+/* S-1c: WORD tokens refused for exceeding a counted string's 255 chars. */
+uint32_t string_word_word_refusals(void);
+
 #endif /* STRING_WORDS_H */

src/word_source/string_words.c

@@ -75,9 +75,12 @@ static inline int ensure_input(VM *vm) {
     return err;
 }
 
-/* Static VM-backed scratch buffer for WORD (allocated on first use) */
-#define WORD_SCRATCH_CAP 64
-static vaddr_t word_scratch_addr = 0;
+/* S-1c: WORD's buffer is per VM now (vm->word_buf, vm_input_ensure()). A
+ * token too long for a counted string (> 255 chars) is refused, logged and
+ * counted here -- never silently truncated. */
+static uint32_t g_word_too_long;
+
+uint32_t string_word_word_refusals(void) { return g_word_too_long; }
 
 /* Helper function to convert string to number (base-10 only here) */
 static int convert_string_to_number(const char *str, size_t len, cell_t *result) {
@@ -248,33 +251,31 @@ void string_word_word(VM *vm) {
     while ((size_t) ip < tib_len && tib[ip] != (unsigned char) delimiter) ip++;
     size_t end = (size_t) ip;
     size_t word_len = end - start;
-    if (word_len > WORD_SCRATCH_CAP - 2) word_len = WORD_SCRATCH_CAP - 2;
-
-    /* Allocate scratch once */
-    if (word_scratch_addr == 0) {
-        void *p = vm_allot(vm, WORD_SCRATCH_CAP);
-        if (!p) {
-            vm->error = 1;
-            return;
-        }
-        word_scratch_addr = vaddr_from_ptr(vm, p);
+    if (word_len > WORD_BUFFER_SIZE - 2) {
+        /* Refused whole: the delimiter goes back on the stack and >IN is
+         * left where it was, so nothing is consumed. */
+        g_word_too_long++;
+        log_message(LOG_ERROR, "WORD: token over 255 chars refused");
+        vm_push(vm, c);
+        vm->error = 1;
+        return;
     }
 
-    /* Build counted string at scratch */
-    uint8_t *wb = vm_ptr(vm, word_scratch_addr);
+    /* Build the counted string in this VM's own WORD buffer */
+    uint8_t *wb = vm->word_buf;
     if (!wb) {
         vm->error = 1;
         return;
     }
     wb[0] = (uint8_t) word_len;
     if (word_len) memcpy(&wb[1], &tib[start], word_len);
-    if (word_len + 1 < WORD_SCRATCH_CAP) wb[word_len + 1] = '\0'; /* safety */
+    wb[word_len + 1] = '\0'; /* safety */
 
     /* Update >IN to char after the delimiter (if any) */
     while ((size_t) ip < tib_len && tib[ip] == (unsigned char) delimiter) ip++;
     *inp = ip;
 
-    vm_push(vm, CELL(word_scratch_addr));
+    vm_push(vm, CELL(vaddr_from_ptr(vm, wb)));
 }
 
 /* >IN ( -- addr )  Input stream pointer cell (VM address) */

src/word_source/system_words.c

@@ -90,7 +90,16 @@ static void reset_vm_state(VM *vm, int cold_start) {
     if (cold_start) {
         /* In a complete system, this would restore a boot image.
            For now we keep a minimal fence by not crushing the base dictionary. */
-        if (vm->here > 1024) vm->here = 1024;
+        if (vm->here > 1024) {
+            /* S-1c: never below the input buffers allotted at vm_init()
+             * (TIB/>IN/SPAN/WORD buffer end past 1024). */
+            size_t floor = 1024;
+            if (vm->word_buf) {
+                size_t buf_end = (size_t)(vm->word_buf - vm->memory) + WORD_BUFFER_SIZE;
+                if (buf_end > floor) floor = buf_end;
+            }
+            if (vm->here > floor) vm->here = floor;
+        }
     }
 
     system_running = 1;