LithosAnanake/proof/StarForth_Defining_Words.thy

theory StarForth_Defining_Words
  imports StarForth_Base StarForth_Memory_Words
begin

(* =========================================================================
   Mirrors: src/word_source/defining_words.c
   Registers: : ; CREATE VARIABLE CONSTANT IMMEDIATE STATE [ ] FORGET
              COMPILE [COMPILE] LIT LITERAL does_rt DOES> DEFER IS DEFER@

   ── Duplicate-registration finding (corrects a StarForth_Dictionary_
      Manipulation_Words.thy note) ────────────────────────────────────────
   `src/word_registry.c` registers dictionary_manipulation_words.c's `[`,
   `]`, `STATE` (Module 13, line 122) BEFORE defining_words.c's `[`, `]`,
   `STATE` (Module 17, line 126). FORTH dictionary lookup finds the MOST
   RECENT definition of a name first, so defining_words.c's versions are
   the only ones ever reachable -- dictionary_manipulation_words.c's `[`/
   `]`/`STATE`/`INTERPRET` are permanently shadowed, dead code from the
   moment boot registration completes.

   This also CORRECTS that file's finding, not just supersedes it: its
   `[`/`]`/`STATE` write/read a dead file-scope `static cell_t
   state_variable`, cross-VM-shared and never the real per-VM STATE. The
   LIVE versions here (defining_word_left_bracket/right_bracket/state) use
   `vm->state_addr` (include/vm.h:452) -- a genuine per-VM VM-memory
   address, correctly written via `vm_store_cell`. The dead-static bug is
   real IN THE SHADOWED CODE, but does not reach runtime: no VM instance's
   `[`/`]`/`STATE` actually touches that static. Added `state_addr :: nat`
   to vm_state (StarForth_Base.thy) to model this correctly.

   ── Scope of this file ──────────────────────────────────────────────────
   Split three ways:
   1. Mode/flag/address words ([, ], STATE, IMMEDIATE) -- fully modelled,
      provable against `vm_mode`/`state_addr`/`memory`/`dictionary`/
      `latest_id`.
   2. `:` / `;` -- guard conditions modelled; `:`'s STATE/mode-setting half
      of `vm_enter_compile_mode` is modelled (identical shape to `]`), but
      the dictionary-entry-creation half (`vm_create_word` -> a fresh
      DictEntry with `vm->compiling_word` tracking it) is NOT modelled --
      see the finding below. `;`'s entire effect beyond the guard
      (`vm_exit_compile_mode`: find/compile EXIT, clear WORD_SMUDGED, set
      WORD_COMPILED, evict hot-words cache) is NOT modelled for the same
      reason plus dependence on the hot-words cache, itself never modelled
      in this suite.
   3. Everything else (CREATE, VARIABLE, CONSTANT, FORGET, COMPILE,
      [COMPILE], LIT, LITERAL, does_rt, DOES>, DEFER, IS, DEFER@, and the
      three defining-runtime functions CREATE/VARIABLE/CONSTANT install) --
      NOT modelled. Each hits one or more of the same three model gaps,
      named once here rather than repeated per word:

      (a) DICTIONARY-ENTRY CREATION is not modelled anywhere in this proof
          suite. `dictionary :: nat \<Rightarrow> dict_entry option` (StarForth_
          Base.thy:498) is treated as a fixed, pre-populated table by every
          theory so far -- FIND/TRAVERSE/etc. in StarForth_Dictionary_
          Manipulation_Words.thy only READ it. This is the first file in
          the sweep whose primary job IS insertion (`:`, CREATE, VARIABLE,
          CONSTANT, DEFER all call `vm_create_word`). `vm_create_word`
          itself parses no input (name arrives pre-parsed) but allocates a
          new DictEntry, links it into `vm->latest`, and returns a raw
          `DictEntry*` the caller mutates directly (`entry->flags |=
          WORD_SMUDGED`, etc.) -- none of which has a counterpart in the
          word_id-indexed abstract model with no live pointer aliasing.
          This is a materially bigger gap than the raw-pointer-navigation
          gap already flagged in dictionary_manipulation_words.c (which
          only reads), and is the single largest finding of this file.

      (b) DATA-FIELD (DF) ADDRESSING: `dict_entry` (StarForth_Base.thy:293)
          has no field corresponding to a DictEntry's data-field cell (the
          storage `vm_dictionary_get_data_field` returns a pointer into).
          CREATE/VARIABLE/CONSTANT's runtimes, DODOES, and does_rt all
          read or write this cell -- the exact gap already named for
          `>BODY` in StarForth_Dictionary_Manipulation_Words.thy
          (`to_body_not_modelled`). Same root cause, different words.

      (c) MUTABLE PER-ENTRY DISPATCH: `word_table` (StarForth_Base.thy:626)
          is a fixed, uninterpreted global constant -- by design (see that
          section's comment), not a per-VM-instance mutable field. DEFER's
          `IS` reassigns an entry's *effective* dispatch target at runtime
          (stored in the DF cell and read by `defining_runtime_defer`); a
          fixed `word_table` cannot express this at all, independent of
          gap (b).

      LIT additionally treats the top return-stack cell as a raw C
      `cell_t*` threaded-code instruction pointer, advanced with C pointer
      arithmetic (`rip++`) and dereferenced directly -- NOT as a VM address
      resolved through `vm_ptr`/`vm_addr_ok` the way control_words.c's
      return-stack-held IP values were (see StarForth_Control_Words.thy's
      resume note: that gap turned out to already be covered by `mem_read`
      on VM-address-valued return-stack entries). LIT's IP is a genuinely
      different, raw-host-pointer usage of the same field; the list-based
      `return_stack :: cell list` model has no way to hold or advance a
      host pointer.
   ======================================================================== *)

definition WORD_IMMEDIATE :: nat where "WORD_IMMEDIATE = 0x80"

(* ── [ ( -- ) : interpret mode, LIVE version (see file header) ──────────── *)
(* C: vm_store_cell(vm, vm->state_addr, 0); vm->mode = MODE_INTERPRET. *)

definition forth_d_left_bracket :: "vm_state \<Rightarrow> vm_state" where
  "forth_d_left_bracket vm =
     vm\<lparr>memory  := mem_write (memory vm) (state_addr vm) 0,
        vm_mode := ModeInterpret\<rparr>"

lemma d_left_bracket_sets_interpret:
  "vm_mode (forth_d_left_bracket vm) = ModeInterpret"
  by (simp add: forth_d_left_bracket_def)

lemma d_left_bracket_writes_state_cell:
  "mem_read (memory (forth_d_left_bracket vm)) (state_addr vm) = 0"
  by (simp add: forth_d_left_bracket_def mem_read_def mem_write_def)

lemma d_left_bracket_data_stack_unchanged:
  "data_stack (forth_d_left_bracket vm) = data_stack vm"
  by (simp add: forth_d_left_bracket_def)

lemma d_left_bracket_never_errors:
  "vm_error (forth_d_left_bracket vm) = vm_error vm"
  by (simp add: forth_d_left_bracket_def)

(* ── ] ( -- ) : compile mode, LIVE version ───────────────────────────────── *)
(* C: vm_store_cell(vm, vm->state_addr, (cell_t)-1); vm->mode = MODE_COMPILE. *)

definition forth_d_right_bracket :: "vm_state \<Rightarrow> vm_state" where
  "forth_d_right_bracket vm =
     vm\<lparr>memory  := mem_write (memory vm) (state_addr vm) (-1),
        vm_mode := ModeCompile\<rparr>"

lemma d_right_bracket_sets_compile:
  "vm_mode (forth_d_right_bracket vm) = ModeCompile"
  by (simp add: forth_d_right_bracket_def)

lemma d_right_bracket_writes_state_cell:
  "mem_read (memory (forth_d_right_bracket vm)) (state_addr vm) = -1"
  by (simp add: forth_d_right_bracket_def mem_read_def mem_write_def)

lemma d_right_bracket_data_stack_unchanged:
  "data_stack (forth_d_right_bracket vm) = data_stack vm"
  by (simp add: forth_d_right_bracket_def)

lemma d_right_bracket_never_errors:
  "vm_error (forth_d_right_bracket vm) = vm_error vm"
  by (simp add: forth_d_right_bracket_def)

lemma d_bracket_right_then_left:
  "vm_mode (forth_d_left_bracket (forth_d_right_bracket vm)) = ModeInterpret"
  by (simp add: forth_d_left_bracket_def)

lemma d_bracket_left_then_right:
  "vm_mode (forth_d_right_bracket (forth_d_left_bracket vm)) = ModeCompile"
  by (simp add: forth_d_right_bracket_def)

(* ── STATE ( -- addr ) : LIVE version, pushes a real VM address ─────────── *)
(* C: vm_push(vm, (cell_t)vm->state_addr). Unlike the shadowed dictionary_
   manipulation_words.c version (which pushed the address of a dead host
   static, and was left unmodelled), this pushes `state_addr` -- a genuine
   per-VM field, so this word IS modellable. *)

definition forth_d_state :: "vm_state \<Rightarrow> vm_state" where
  "forth_d_state vm =
    (if ds_full vm
     then set_error vm
     else vm\<lparr>data_stack := word_of_nat (state_addr vm) # data_stack vm\<rparr>)"

lemma d_state_normal:
  assumes "\<not> ds_full vm"
  shows "data_stack (forth_d_state vm) = word_of_nat (state_addr vm) # data_stack vm"
  by (simp add: forth_d_state_def assms)

lemma d_state_overflow:
  assumes "ds_full vm"
  shows "vm_error (forth_d_state vm)"
  by (simp add: forth_d_state_def set_error_def assms)

lemma d_state_preserves_state_addr:
  "state_addr (forth_d_state vm) = state_addr vm"
  by (simp add: forth_d_state_def set_error_def)

(* ── IMMEDIATE ( -- ) : mark latest word immediate, no mode guard ───────── *)
(* C: error if vm->latest is NULL; else vm->latest->flags |= WORD_IMMEDIATE.
   Unlike HIDDEN (dictionary_manipulation_words.c), there is no compile-mode
   guard at all. *)

definition forth_immediate :: "vm_state \<Rightarrow> vm_state" where
  "forth_immediate vm =
    (case latest_id vm of
       None \<Rightarrow> set_error vm
     | Some wid \<Rightarrow>
         (case dictionary vm wid of
            None \<Rightarrow> set_error vm
          | Some e \<Rightarrow>
              vm\<lparr>dictionary := (dictionary vm)
                   (wid := Some (e\<lparr>de_flags := de_flags e OR WORD_IMMEDIATE\<rparr>))\<rparr>))"

lemma immediate_requires_latest:
  assumes "latest_id vm = None"
  shows "vm_error (forth_immediate vm)"
  by (simp add: forth_immediate_def set_error_def assms)

lemma immediate_requires_latest_present_in_dict:
  assumes "latest_id vm = Some wid"
  assumes "dictionary vm wid = None"
  shows "vm_error (forth_immediate vm)"
  by (simp add: forth_immediate_def set_error_def assms)

lemma immediate_sets_flag:
  assumes "latest_id vm = Some wid"
  assumes "dictionary vm wid = Some e"
  shows "\<exists>e'. dictionary (forth_immediate vm) wid = Some e' \<and>
              de_flags e' = de_flags e OR WORD_IMMEDIATE"
  using assms by (simp add: forth_immediate_def)

lemma immediate_data_stack_unchanged:
  "data_stack (forth_immediate vm) = data_stack vm"
  by (auto simp: forth_immediate_def set_error_def split: option.split)

lemma immediate_no_mode_guard:
  \<comment> \<open>Unlike HIDDEN, IMMEDIATE has no `vm_mode vm \<noteq> ModeCompile` check at
     all -- when the latest-word guards above are satisfied, its error
     status is exactly whatever it was on entry (no NEW error is raised by
     a compile-mode check, since there is none). Stated explicitly since
     every other flag-setting word in this sweep (SMUDGE, HIDDEN) DOES gate
     on compile mode.\<close>
  assumes "latest_id vm = Some wid" "dictionary vm wid = Some e"
  shows "vm_error (forth_immediate vm) = vm_error vm"
  using assms by (simp add: forth_immediate_def)

(* ── : ( "name" -- ) : nested-guard + mode/STATE half only ──────────────── *)
(* C (defining_word_colon + vm_enter_compile_mode): error if already in
   MODE_COMPILE (nested ':' is illegal per FORTH-79); else vm->mode =
   MODE_COMPILE, vm->state_var = -1, vm_store_cell(vm, vm->state_addr, -1),
   THEN vm_create_word(...) -- the entry-creation half, see file header
   finding (a), is NOT modelled. Modelled here: guard + the mode/state_var/
   state_addr-cell effect, which is state-only and has the identical shape
   to `]` plus the extra `state_var` write `]` itself does not do. *)

definition forth_colon_guard :: "vm_state \<Rightarrow> vm_state" where
  "forth_colon_guard vm =
    (if vm_mode vm = ModeCompile
     then set_error vm
     else vm\<lparr>vm_mode := ModeCompile,
              state_var := -1,
              memory := mem_write (memory vm) (state_addr vm) (-1)\<rparr>)"

lemma colon_nested_errors:
  assumes "vm_mode vm = ModeCompile"
  shows "vm_error (forth_colon_guard vm)"
  by (simp add: forth_colon_guard_def set_error_def assms)

lemma colon_sets_compile_mode:
  assumes "vm_mode vm \<noteq> ModeCompile"
  shows "vm_mode (forth_colon_guard vm) = ModeCompile"
  by (simp add: forth_colon_guard_def assms)

lemma colon_sets_state_var:
  assumes "vm_mode vm \<noteq> ModeCompile"
  shows "state_var (forth_colon_guard vm) = -1"
  by (simp add: forth_colon_guard_def assms)

lemma colon_writes_state_cell:
  assumes "vm_mode vm \<noteq> ModeCompile"
  shows "mem_read (memory (forth_colon_guard vm)) (state_addr vm) = -1"
  by (simp add: forth_colon_guard_def mem_read_def mem_write_def assms)

lemma colon_guard_not_full_colon: True
  \<comment> \<open>forth_colon_guard is NOT a full model of `:` -- it omits the
     dictionary-entry-creation half (`vm_create_word`, `vm->compiling_word`,
     WORD_SMUDGED, the DF write of the threaded-body start address). See
     file header finding (a)/(b). Named so the omission is greppable.\<close>
  by simp

(* ── ; ( -- ) : compile-mode guard only ──────────────────────────────────── *)
(* C: error unless vm->mode == MODE_COMPILE; else calls vm_exit_compile_mode,
   entirely unmodelled (finds/compiles EXIT, flips WORD_SMUDGED/WORD_COMPILED,
   evicts hot-words cache -- none modelled in this suite). *)

definition forth_semicolon_guard :: "vm_state \<Rightarrow> vm_state" where
  "forth_semicolon_guard vm = (if vm_mode vm \<noteq> ModeCompile then set_error vm else vm)"

lemma semicolon_requires_compile_mode:
  assumes "vm_mode vm \<noteq> ModeCompile"
  shows "vm_error (forth_semicolon_guard vm)"
  by (simp add: forth_semicolon_guard_def set_error_def assms)

lemma semicolon_guard_not_full_semicolon: True
  \<comment> \<open>forth_semicolon_guard covers only the guard raised directly in
     defining_word_semicolon. vm_exit_compile_mode's own effects (EXIT
     lookup+compile, WORD_SMUDGED/WORD_COMPILED flag flip, hot-words cache
     eviction) are entirely unmodelled -- none of EXIT-lookup, per-entry
     mutable flags via a live pointer, or the hot-words cache have any
     counterpart in this suite's abstract model.\<close>
  by simp

(* ── Everything else in this file -- NOT MODELLED ─────────────────────────
   See file header findings (a) dictionary-entry creation, (b) data-field
   addressing, (c) mutable per-entry dispatch. One sentinel lemma per word/
   helper, matching the StarForth_Dictionary_Manipulation_Words.thy
   convention. *)

lemma create_not_modelled: True        \<comment> \<open>CREATE: vm_create_word (gap a) + DF write of captured DFA (gap b).\<close>
  by simp
lemma variable_not_modelled: True      \<comment> \<open>VARIABLE: vm_allot + vm_create_word (gap a) + DF write of the cell's address (gap b).\<close>
  by simp
lemma constant_not_modelled: True      \<comment> \<open>CONSTANT: vm_create_word (gap a) + DF write of the popped value (gap b).\<close>
  by simp
lemma create_runtime_not_modelled: True   \<comment> \<open>defining_runtime_create: reads current_executing_entry's DF cell (gap b).\<close>
  by simp
lemma variable_runtime_not_modelled: True \<comment> \<open>defining_runtime_variable: reads current_executing_entry's DF cell (gap b).\<close>
  by simp
lemma constant_runtime_not_modelled: True \<comment> \<open>defining_runtime_constant: reads current_executing_entry's DF cell (gap b).\<close>
  by simp
lemma lit_not_modelled: True           \<comment> \<open>LIT: reads/advances the return-stack top as a raw C cell_t* threaded-code IP -- see file header, distinct from control_words.c's already-resolved IP-as-vaddr usage.\<close>
  by simp
lemma literal_not_modelled: True       \<comment> \<open>LITERAL: compiles a literal into threaded code via vm_compile_literal -- depends on the same unmodelled compile-target machinery as `:`/COMPILE.\<close>
  by simp
lemma dodoes_not_modelled: True        \<comment> \<open>defining_runtime_dodoes: DF/PFA layout (gap b) + runs a raw threaded-code interpreter loop over cell_t* IPs (gap c-adjacent, distinct mechanism from vm_ip).\<close>
  by simp
lemma does_rt_not_modelled: True       \<comment> \<open>defining_runtime_does_rt: patches vm->latest's DF (gap b) and reassigns its func pointer to defining_runtime_dodoes (gap c).\<close>
  by simp
lemma does_greater_not_modelled: True  \<comment> \<open>DOES>: compiles does_rt + EXIT into the defining word's body -- same unmodelled compile-target machinery as `:`.\<close>
  by simp
lemma compile_not_modelled: True       \<comment> \<open>COMPILE: vm_find_word (parse+lookup, same class as FIND, already flagged not-modelled) + vm_compile_word.\<close>
  by simp
lemma bracket_compile_not_modelled: True \<comment> \<open>[COMPILE]: identical body to COMPILE (defining_word_bracket_compile IS defining_word_compile).\<close>
  by simp
lemma forget_not_modelled: True        \<comment> \<open>FORGET: walks vm->latest's raw linked chain by name, frees C structs, and rewinds `here` from a DF read (gap a/b combined) -- categorically the same class of gap as `block_words.c`'s cache-subsystem deferrals: a whole-subsystem project, not a one-word extension.\<close>
  by simp
lemma defer_not_modelled: True         \<comment> \<open>DEFER: vm_create_word (gap a) with a zeroed DF slot (gap b).\<close>
  by simp
lemma defer_runtime_not_modelled: True \<comment> \<open>defining_runtime_defer: reads a DictEntry* out of the DF cell (gap b) and calls through it (gap c).\<close>
  by simp
lemma is_not_modelled: True            \<comment> \<open>IS: vm_find_word (parse+lookup) + writes an XT into the target's DF cell (gap b) -- the mutable-dispatch mechanism of gap (c).\<close>
  by simp
lemma defer_fetch_not_modelled: True   \<comment> \<open>DEFER@: vm_find_word + reads the DF cell (gap b).\<close>
  by simp

end