tcl: tick Phase 1 parser checkboxes, update progress log

lib/js/conformance.sh

@@ -49,8 +49,6 @@ trap "rm -f $TMPFILE" EXIT
   echo '(load "lib/js/transpile.sx")'
   echo '(epoch 5)'
   echo '(load "lib/js/runtime.sx")'
-  echo '(epoch 6)'
-  echo '(load "lib/js/regex.sx")'
 
   epoch=100
   for f in "${FIXTURES[@]}"; do

lib/js/regex.sx

@@ -1,943 +0,0 @@
-;; lib/js/regex.sx — pure-SX recursive backtracking regex engine
-;;
-;; Installed via (js-regex-platform-override! ...) at load time.
-;; Covers: character classes (\d\w\s . [abc] [^abc] [a-z]),
-;;   anchors (^ $ \b \B), quantifiers (* + ? {n,m} lazy variants),
-;;   groups (capturing + non-capturing), alternation (a|b),
-;;   flags: i (case-insensitive), g (global), m (multiline).
-;;
-;; Architecture:
-;;   1. rx-parse-pattern  — pattern string → compiled node list
-;;   2. rx-match-nodes    — recursive backtracker
-;;   3. rx-exec / rx-test — public interface
-;;   4. Install as {:test rx-test :exec rx-exec}
-
-;; ── Utilities ─────────────────────────────────────────────────────
-
-(define
-  rx-char-at
-  (fn (s i) (if (and (>= i 0) (< i (len s))) (char-at s i) "")))
-
-(define
-  rx-digit?
-  (fn
-    (c)
-    (and (not (= c "")) (>= (char-code c) 48) (<= (char-code c) 57))))
-
-(define
-  rx-word?
-  (fn
-    (c)
-    (and
-      (not (= c ""))
-      (or
-        (and (>= (char-code c) 65) (<= (char-code c) 90))
-        (and (>= (char-code c) 97) (<= (char-code c) 122))
-        (and (>= (char-code c) 48) (<= (char-code c) 57))
-        (= c "_")))))
-
-(define
-  rx-space?
-  (fn
-    (c)
-    (or (= c " ") (= c "\t") (= c "\n") (= c "\r") (= c "\\f") (= c ""))))
-
-(define rx-newline? (fn (c) (or (= c "\n") (= c "\r"))))
-
-(define
-  rx-downcase-char
-  (fn
-    (c)
-    (let
-      ((cc (char-code c)))
-      (if (and (>= cc 65) (<= cc 90)) (char-from-code (+ cc 32)) c))))
-
-(define
-  rx-char-eq?
-  (fn
-    (a b ci?)
-    (if ci? (= (rx-downcase-char a) (rx-downcase-char b)) (= a b))))
-
-(define
-  rx-parse-int
-  (fn
-    (pat i acc)
-    (let
-      ((c (rx-char-at pat i)))
-      (if
-        (rx-digit? c)
-        (rx-parse-int pat (+ i 1) (+ (* acc 10) (- (char-code c) 48)))
-        (list acc i)))))
-
-(define
-  rx-hex-digit-val
-  (fn
-    (c)
-    (cond
-      ((and (>= (char-code c) 48) (<= (char-code c) 57))
-        (- (char-code c) 48))
-      ((and (>= (char-code c) 65) (<= (char-code c) 70))
-        (+ 10 (- (char-code c) 65)))
-      ((and (>= (char-code c) 97) (<= (char-code c) 102))
-        (+ 10 (- (char-code c) 97)))
-      (else -1))))
-
-(define
-  rx-parse-hex-n
-  (fn
-    (pat i n acc)
-    (if
-      (= n 0)
-      (list (char-from-code acc) i)
-      (let
-        ((v (rx-hex-digit-val (rx-char-at pat i))))
-        (if
-          (< v 0)
-          (list (char-from-code acc) i)
-          (rx-parse-hex-n pat (+ i 1) (- n 1) (+ (* acc 16) v)))))))
-
-;; ── Pattern compiler ──────────────────────────────────────────────
-
-;; Node types (stored in dicts with "__t__" key):
-;;   literal  : {:__t__ "literal" :__c__ char}
-;;   any      : {:__t__ "any"}
-;;   class-d  : {:__t__ "class-d"  :__neg__ bool}
-;;   class-w  : {:__t__ "class-w"  :__neg__ bool}
-;;   class-s  : {:__t__ "class-s"  :__neg__ bool}
-;;   char-class: {:__t__ "char-class" :__neg__ bool :__items__ list}
-;;   anchor-start / anchor-end / anchor-word / anchor-nonword
-;;   quant    : {:__t__ "quant" :__node__ n :__min__ m :__max__ mx :__lazy__ bool}
-;;   group    : {:__t__ "group" :__idx__ i :__nodes__ list}
-;;   ncgroup  : {:__t__ "ncgroup" :__nodes__ list}
-;;   alt      : {:__t__ "alt" :__branches__ list-of-node-lists}
-
-;; parse one escape after `\`, returns (node new-i)
-(define
-  rx-parse-escape
-  (fn
-    (pat i)
-    (let
-      ((c (rx-char-at pat i)))
-      (cond
-        ((= c "d") (list (dict "__t__" "class-d" "__neg__" false) (+ i 1)))
-        ((= c "D") (list (dict "__t__" "class-d" "__neg__" true) (+ i 1)))
-        ((= c "w") (list (dict "__t__" "class-w" "__neg__" false) (+ i 1)))
-        ((= c "W") (list (dict "__t__" "class-w" "__neg__" true) (+ i 1)))
-        ((= c "s") (list (dict "__t__" "class-s" "__neg__" false) (+ i 1)))
-        ((= c "S") (list (dict "__t__" "class-s" "__neg__" true) (+ i 1)))
-        ((= c "b") (list (dict "__t__" "anchor-word") (+ i 1)))
-        ((= c "B") (list (dict "__t__" "anchor-nonword") (+ i 1)))
-        ((= c "n") (list (dict "__t__" "literal" "__c__" "\n") (+ i 1)))
-        ((= c "r") (list (dict "__t__" "literal" "__c__" "\r") (+ i 1)))
-        ((= c "t") (list (dict "__t__" "literal" "__c__" "\t") (+ i 1)))
-        ((= c "f") (list (dict "__t__" "literal" "__c__" "\\f") (+ i 1)))
-        ((= c "v") (list (dict "__t__" "literal" "__c__" "") (+ i 1)))
-        ((= c "u")
-          (let
-            ((res (rx-parse-hex-n pat (+ i 1) 4 0)))
-            (list (dict "__t__" "literal" "__c__" (nth res 0)) (nth res 1))))
-        ((= c "x")
-          (let
-            ((res (rx-parse-hex-n pat (+ i 1) 2 0)))
-            (list (dict "__t__" "literal" "__c__" (nth res 0)) (nth res 1))))
-        (else (list (dict "__t__" "literal" "__c__" c) (+ i 1)))))))
-
-;; parse a char-class item inside [...], returns (item new-i)
-(define
-  rx-parse-class-item
-  (fn
-    (pat i)
-    (let
-      ((c (rx-char-at pat i)))
-      (cond
-        ((= c "\\")
-          (let
-            ((esc (rx-parse-escape pat (+ i 1))))
-            (let
-              ((node (nth esc 0)) (ni (nth esc 1)))
-              (let
-                ((t (get node "__t__")))
-                (cond
-                  ((= t "class-d")
-                    (list
-                      (dict "kind" "class-d" "neg" (get node "__neg__"))
-                      ni))
-                  ((= t "class-w")
-                    (list
-                      (dict "kind" "class-w" "neg" (get node "__neg__"))
-                      ni))
-                  ((= t "class-s")
-                    (list
-                      (dict "kind" "class-s" "neg" (get node "__neg__"))
-                      ni))
-                  (else
-                    (let
-                      ((lc (get node "__c__")))
-                      (if
-                        (and
-                          (= (rx-char-at pat ni) "-")
-                          (not (= (rx-char-at pat (+ ni 1)) "]")))
-                        (let
-                          ((hi-c (rx-char-at pat (+ ni 1))))
-                          (list
-                            (dict "kind" "range" "lo" lc "hi" hi-c)
-                            (+ ni 2)))
-                        (list (dict "kind" "lit" "c" lc) ni)))))))))
-        (else
-          (if
-            (and
-              (not (= c ""))
-              (= (rx-char-at pat (+ i 1)) "-")
-              (not (= (rx-char-at pat (+ i 2)) "]"))
-              (not (= (rx-char-at pat (+ i 2)) "")))
-            (let
-              ((hi-c (rx-char-at pat (+ i 2))))
-              (list (dict "kind" "range" "lo" c "hi" hi-c) (+ i 3)))
-            (list (dict "kind" "lit" "c" c) (+ i 1))))))))
-
-(define
-  rx-parse-class-items
-  (fn
-    (pat i items)
-    (let
-      ((c (rx-char-at pat i)))
-      (if
-        (or (= c "]") (= c ""))
-        (list items i)
-        (let
-          ((res (rx-parse-class-item pat i)))
-          (begin
-            (append! items (nth res 0))
-            (rx-parse-class-items pat (nth res 1) items)))))))
-
-;; parse a sequence until stop-ch or EOF; returns (nodes new-i groups-count)
-(define
-  rx-parse-seq
-  (fn
-    (pat i stop-ch ds)
-    (let
-      ((c (rx-char-at pat i)))
-      (cond
-        ((= c "") (list (get ds "nodes") i (get ds "groups")))
-        ((= c stop-ch) (list (get ds "nodes") i (get ds "groups")))
-        ((= c "|") (rx-parse-alt-rest pat i ds))
-        (else
-          (let
-            ((res (rx-parse-atom pat i ds)))
-            (let
-              ((node (nth res 0)) (ni (nth res 1)) (ds2 (nth res 2)))
-              (let
-                ((qres (rx-parse-quant pat ni node)))
-                (begin
-                  (append! (get ds2 "nodes") (nth qres 0))
-                  (rx-parse-seq pat (nth qres 1) stop-ch ds2))))))))))
-
-;; when we hit | inside a sequence, collect all alternatives
-(define
-  rx-parse-alt-rest
-  (fn
-    (pat i ds)
-    (let
-      ((left-branch (get ds "nodes")) (branches (list)))
-      (begin
-        (append! branches left-branch)
-        (rx-parse-alt-branches pat i (get ds "groups") branches)))))
-
-(define
-  rx-parse-alt-branches
-  (fn
-    (pat i n-groups branches)
-    (let
-      ((new-nodes (list)) (ds2 (dict "groups" n-groups "nodes" new-nodes)))
-      (let
-        ((res (rx-parse-seq pat (+ i 1) "|" ds2)))
-        (begin
-          (append! branches (nth res 0))
-          (let
-            ((ni2 (nth res 1)) (g2 (nth res 2)))
-            (if
-              (= (rx-char-at pat ni2) "|")
-              (rx-parse-alt-branches pat ni2 g2 branches)
-              (list
-                (list (dict "__t__" "alt" "__branches__" branches))
-                ni2
-                g2))))))))
-
-;; parse quantifier suffix, returns (node new-i)
-(define
-  rx-parse-quant
-  (fn
-    (pat i node)
-    (let
-      ((c (rx-char-at pat i)))
-      (cond
-        ((= c "*")
-          (let
-            ((lazy? (= (rx-char-at pat (+ i 1)) "?")))
-            (list
-              (dict
-                "__t__"
-                "quant"
-                "__node__"
-                node
-                "__min__"
-                0
-                "__max__"
-                -1
-                "__lazy__"
-                lazy?)
-              (if lazy? (+ i 2) (+ i 1)))))
-        ((= c "+")
-          (let
-            ((lazy? (= (rx-char-at pat (+ i 1)) "?")))
-            (list
-              (dict
-                "__t__"
-                "quant"
-                "__node__"
-                node
-                "__min__"
-                1
-                "__max__"
-                -1
-                "__lazy__"
-                lazy?)
-              (if lazy? (+ i 2) (+ i 1)))))
-        ((= c "?")
-          (let
-            ((lazy? (= (rx-char-at pat (+ i 1)) "?")))
-            (list
-              (dict
-                "__t__"
-                "quant"
-                "__node__"
-                node
-                "__min__"
-                0
-                "__max__"
-                1
-                "__lazy__"
-                lazy?)
-              (if lazy? (+ i 2) (+ i 1)))))
-        ((= c "{")
-          (let
-            ((mres (rx-parse-int pat (+ i 1) 0)))
-            (let
-              ((mn (nth mres 0)) (mi (nth mres 1)))
-              (let
-                ((sep (rx-char-at pat mi)))
-                (cond
-                  ((= sep "}")
-                    (let
-                      ((lazy? (= (rx-char-at pat (+ mi 1)) "?")))
-                      (list
-                        (dict
-                          "__t__"
-                          "quant"
-                          "__node__"
-                          node
-                          "__min__"
-                          mn
-                          "__max__"
-                          mn
-                          "__lazy__"
-                          lazy?)
-                        (if lazy? (+ mi 2) (+ mi 1)))))
-                  ((= sep ",")
-                    (let
-                      ((c2 (rx-char-at pat (+ mi 1))))
-                      (if
-                        (= c2 "}")
-                        (let
-                          ((lazy? (= (rx-char-at pat (+ mi 2)) "?")))
-                          (list
-                            (dict
-                              "__t__"
-                              "quant"
-                              "__node__"
-                              node
-                              "__min__"
-                              mn
-                              "__max__"
-                              -1
-                              "__lazy__"
-                              lazy?)
-                            (if lazy? (+ mi 3) (+ mi 2))))
-                        (let
-                          ((mxres (rx-parse-int pat (+ mi 1) 0)))
-                          (let
-                            ((mx (nth mxres 0)) (mxi (nth mxres 1)))
-                            (let
-                              ((lazy? (= (rx-char-at pat (+ mxi 1)) "?")))
-                              (list
-                                (dict
-                                  "__t__"
-                                  "quant"
-                                  "__node__"
-                                  node
-                                  "__min__"
-                                  mn
-                                  "__max__"
-                                  mx
-                                  "__lazy__"
-                                  lazy?)
-                                (if lazy? (+ mxi 2) (+ mxi 1)))))))))
-                  (else (list node i)))))))
-        (else (list node i))))))
-
-;; parse one atom, returns (node new-i new-ds)
-(define
-  rx-parse-atom
-  (fn
-    (pat i ds)
-    (let
-      ((c (rx-char-at pat i)))
-      (cond
-        ((= c ".") (list (dict "__t__" "any") (+ i 1) ds))
-        ((= c "^") (list (dict "__t__" "anchor-start") (+ i 1) ds))
-        ((= c "$") (list (dict "__t__" "anchor-end") (+ i 1) ds))
-        ((= c "\\")
-          (let
-            ((esc (rx-parse-escape pat (+ i 1))))
-            (list (nth esc 0) (nth esc 1) ds)))
-        ((= c "[")
-          (let
-            ((neg? (= (rx-char-at pat (+ i 1)) "^")))
-            (let
-              ((start (if neg? (+ i 2) (+ i 1))) (items (list)))
-              (let
-                ((res (rx-parse-class-items pat start items)))
-                (let
-                  ((ci (nth res 1)))
-                  (list
-                    (dict
-                      "__t__"
-                      "char-class"
-                      "__neg__"
-                      neg?
-                      "__items__"
-                      items)
-                    (+ ci 1)
-                    ds))))))
-        ((= c "(")
-          (let
-            ((c2 (rx-char-at pat (+ i 1))))
-            (if
-              (and (= c2 "?") (= (rx-char-at pat (+ i 2)) ":"))
-              (let
-                ((inner-nodes (list))
-                  (inner-ds
-                    (dict "groups" (get ds "groups") "nodes" inner-nodes)))
-                (let
-                  ((res (rx-parse-seq pat (+ i 3) ")" inner-ds)))
-                  (list
-                    (dict "__t__" "ncgroup" "__nodes__" (nth res 0))
-                    (+ (nth res 1) 1)
-                    (dict "groups" (nth res 2) "nodes" (get ds "nodes")))))
-              (let
-                ((gidx (+ (get ds "groups") 1)) (inner-nodes (list)))
-                (let
-                  ((inner-ds (dict "groups" gidx "nodes" inner-nodes)))
-                  (let
-                    ((res (rx-parse-seq pat (+ i 1) ")" inner-ds)))
-                    (list
-                      (dict
-                        "__t__"
-                        "group"
-                        "__idx__"
-                        gidx
-                        "__nodes__"
-                        (nth res 0))
-                      (+ (nth res 1) 1)
-                      (dict "groups" (nth res 2) "nodes" (get ds "nodes")))))))))
-        (else (list (dict "__t__" "literal" "__c__" c) (+ i 1) ds))))))
-
-;; top-level compile
-(define
-  rx-compile
-  (fn
-    (pattern)
-    (let
-      ((nodes (list)) (ds (dict "groups" 0 "nodes" nodes)))
-      (let
-        ((res (rx-parse-seq pattern 0 "" ds)))
-        (dict "nodes" (nth res 0) "ngroups" (nth res 2))))))
-
-;; ── Matcher ───────────────────────────────────────────────────────
-
-;; Match a char-class item against character c
-(define
-  rx-item-matches?
-  (fn
-    (item c ci?)
-    (let
-      ((kind (get item "kind")))
-      (cond
-        ((= kind "lit") (rx-char-eq? c (get item "c") ci?))
-        ((= kind "range")
-          (let
-            ((lo (if ci? (rx-downcase-char (get item "lo")) (get item "lo")))
-              (hi
-                (if ci? (rx-downcase-char (get item "hi")) (get item "hi")))
-              (dc (if ci? (rx-downcase-char c) c)))
-            (and
-              (>= (char-code dc) (char-code lo))
-              (<= (char-code dc) (char-code hi)))))
-        ((= kind "class-d")
-          (let ((m (rx-digit? c))) (if (get item "neg") (not m) m)))
-        ((= kind "class-w")
-          (let ((m (rx-word? c))) (if (get item "neg") (not m) m)))
-        ((= kind "class-s")
-          (let ((m (rx-space? c))) (if (get item "neg") (not m) m)))
-        (else false)))))
-
-(define
-  rx-class-items-any?
-  (fn
-    (items c ci?)
-    (if
-      (empty? items)
-      false
-      (if
-        (rx-item-matches? (first items) c ci?)
-        true
-        (rx-class-items-any? (rest items) c ci?)))))
-
-(define
-  rx-class-matches?
-  (fn
-    (node c ci?)
-    (let
-      ((neg? (get node "__neg__")) (items (get node "__items__")))
-      (let
-        ((hit (rx-class-items-any? items c ci?)))
-        (if neg? (not hit) hit)))))
-
-;; Word boundary check
-(define
-  rx-is-word-boundary?
-  (fn
-    (s i slen)
-    (let
-      ((before (if (> i 0) (rx-word? (char-at s (- i 1))) false))
-        (after (if (< i slen) (rx-word? (char-at s i)) false)))
-      (not (= before after)))))
-
-;; ── Core matcher ──────────────────────────────────────────────────
-;;
-;; rx-match-nodes : nodes s i slen ci? mi? groups → end-pos or -1
-;;
-;; Matches `nodes` starting at position `i` in string `s`.
-;; Returns the position after the last character consumed, or -1 on failure.
-;; Mutates `groups` dict to record captures.
-
-(define
-  rx-match-nodes
-  (fn
-    (nodes s i slen ci? mi? groups)
-    (if
-      (empty? nodes)
-      i
-      (let
-        ((node (first nodes)) (rest-nodes (rest nodes)))
-        (let
-          ((t (get node "__t__")))
-          (cond
-            ((= t "literal")
-              (if
-                (and
-                  (< i slen)
-                  (rx-char-eq? (char-at s i) (get node "__c__") ci?))
-                (rx-match-nodes rest-nodes s (+ i 1) slen ci? mi? groups)
-                -1))
-            ((= t "any")
-              (if
-                (and (< i slen) (not (rx-newline? (char-at s i))))
-                (rx-match-nodes rest-nodes s (+ i 1) slen ci? mi? groups)
-                -1))
-            ((= t "class-d")
-              (let
-                ((m (and (< i slen) (rx-digit? (char-at s i)))))
-                (if
-                  (if (get node "__neg__") (not m) m)
-                  (rx-match-nodes rest-nodes s (+ i 1) slen ci? mi? groups)
-                  -1)))
-            ((= t "class-w")
-              (let
-                ((m (and (< i slen) (rx-word? (char-at s i)))))
-                (if
-                  (if (get node "__neg__") (not m) m)
-                  (rx-match-nodes rest-nodes s (+ i 1) slen ci? mi? groups)
-                  -1)))
-            ((= t "class-s")
-              (let
-                ((m (and (< i slen) (rx-space? (char-at s i)))))
-                (if
-                  (if (get node "__neg__") (not m) m)
-                  (rx-match-nodes rest-nodes s (+ i 1) slen ci? mi? groups)
-                  -1)))
-            ((= t "char-class")
-              (if
-                (and (< i slen) (rx-class-matches? node (char-at s i) ci?))
-                (rx-match-nodes rest-nodes s (+ i 1) slen ci? mi? groups)
-                -1))
-            ((= t "anchor-start")
-              (if
-                (or
-                  (= i 0)
-                  (and mi? (rx-newline? (rx-char-at s (- i 1)))))
-                (rx-match-nodes rest-nodes s i slen ci? mi? groups)
-                -1))
-            ((= t "anchor-end")
-              (if
-                (or (= i slen) (and mi? (rx-newline? (rx-char-at s i))))
-                (rx-match-nodes rest-nodes s i slen ci? mi? groups)
-                -1))
-            ((= t "anchor-word")
-              (if
-                (rx-is-word-boundary? s i slen)
-                (rx-match-nodes rest-nodes s i slen ci? mi? groups)
-                -1))
-            ((= t "anchor-nonword")
-              (if
-                (not (rx-is-word-boundary? s i slen))
-                (rx-match-nodes rest-nodes s i slen ci? mi? groups)
-                -1))
-            ((= t "group")
-              (let
-                ((gidx (get node "__idx__"))
-                  (inner (get node "__nodes__")))
-                (let
-                  ((g-end (rx-match-nodes inner s i slen ci? mi? groups)))
-                  (if
-                    (>= g-end 0)
-                    (begin
-                      (dict-set!
-                        groups
-                        (js-to-string gidx)
-                        (substring s i g-end))
-                      (let
-                        ((final-end (rx-match-nodes rest-nodes s g-end slen ci? mi? groups)))
-                        (if
-                          (>= final-end 0)
-                          final-end
-                          (begin
-                            (dict-set! groups (js-to-string gidx) nil)
-                            -1))))
-                    -1))))
-            ((= t "ncgroup")
-              (let
-                ((inner (get node "__nodes__")))
-                (rx-match-nodes
-                  (append inner rest-nodes)
-                  s
-                  i
-                  slen
-                  ci?
-                  mi?
-                  groups)))
-            ((= t "alt")
-              (let
-                ((branches (get node "__branches__")))
-                (rx-try-branches branches rest-nodes s i slen ci? mi? groups)))
-            ((= t "quant")
-              (let
-                ((inner-node (get node "__node__"))
-                  (mn (get node "__min__"))
-                  (mx (get node "__max__"))
-                  (lazy? (get node "__lazy__")))
-                (if
-                  lazy?
-                  (rx-quant-lazy
-                    inner-node
-                    mn
-                    mx
-                    rest-nodes
-                    s
-                    i
-                    slen
-                    ci?
-                    mi?
-                    groups
-                    0)
-                  (rx-quant-greedy
-                    inner-node
-                    mn
-                    mx
-                    rest-nodes
-                    s
-                    i
-                    slen
-                    ci?
-                    mi?
-                    groups
-                    0))))
-            (else -1)))))))
-
-(define
-  rx-try-branches
-  (fn
-    (branches rest-nodes s i slen ci? mi? groups)
-    (if
-      (empty? branches)
-      -1
-      (let
-        ((res (rx-match-nodes (append (first branches) rest-nodes) s i slen ci? mi? groups)))
-        (if
-          (>= res 0)
-          res
-          (rx-try-branches (rest branches) rest-nodes s i slen ci? mi? groups))))))
-
-;; Greedy: expand as far as possible, then try rest from the longest match
-;; Strategy: recurse forward (extend first); only try rest when extension fails
-(define
-  rx-quant-greedy
-  (fn
-    (inner-node mn mx rest-nodes s i slen ci? mi? groups count)
-    (let
-      ((can-extend (and (< i slen) (or (= mx -1) (< count mx)))))
-      (if
-        can-extend
-        (let
-          ((ni (rx-match-one inner-node s i slen ci? mi? groups)))
-          (if
-            (>= ni 0)
-            (let
-              ((res (rx-quant-greedy inner-node mn mx rest-nodes s ni slen ci? mi? groups (+ count 1))))
-              (if
-                (>= res 0)
-                res
-                (if
-                  (>= count mn)
-                  (rx-match-nodes rest-nodes s i slen ci? mi? groups)
-                  -1)))
-            (if
-              (>= count mn)
-              (rx-match-nodes rest-nodes s i slen ci? mi? groups)
-              -1)))
-        (if
-          (>= count mn)
-          (rx-match-nodes rest-nodes s i slen ci? mi? groups)
-          -1)))))
-
-;; Lazy: try rest first, extend only if rest fails
-(define
-  rx-quant-lazy
-  (fn
-    (inner-node mn mx rest-nodes s i slen ci? mi? groups count)
-    (if
-      (>= count mn)
-      (let
-        ((res (rx-match-nodes rest-nodes s i slen ci? mi? groups)))
-        (if
-          (>= res 0)
-          res
-          (if
-            (and (< i slen) (or (= mx -1) (< count mx)))
-            (let
-              ((ni (rx-match-one inner-node s i slen ci? mi? groups)))
-              (if
-                (>= ni 0)
-                (rx-quant-lazy
-                  inner-node
-                  mn
-                  mx
-                  rest-nodes
-                  s
-                  ni
-                  slen
-                  ci?
-                  mi?
-                  groups
-                  (+ count 1))
-                -1))
-            -1)))
-      (if
-        (< i slen)
-        (let
-          ((ni (rx-match-one inner-node s i slen ci? mi? groups)))
-          (if
-            (>= ni 0)
-            (rx-quant-lazy
-              inner-node
-              mn
-              mx
-              rest-nodes
-              s
-              ni
-              slen
-              ci?
-              mi?
-              groups
-              (+ count 1))
-            -1))
-        -1))))
-
-;; Match a single node at position i, return new pos or -1
-(define
-  rx-match-one
-  (fn
-    (node s i slen ci? mi? groups)
-    (rx-match-nodes (list node) s i slen ci? mi? groups)))
-
-;; ── Engine entry points ───────────────────────────────────────────
-
-;; Try matching at exactly position i. Returns result dict or nil.
-(define
-  rx-try-at
-  (fn
-    (compiled s i slen ci? mi?)
-    (let
-      ((nodes (get compiled "nodes")) (ngroups (get compiled "ngroups")))
-      (let
-        ((groups (dict)))
-        (let
-          ((end (rx-match-nodes nodes s i slen ci? mi? groups)))
-          (if
-            (>= end 0)
-            (dict "start" i "end" end "groups" groups "ngroups" ngroups)
-            nil))))))
-
-;; Find first match scanning from search-start.
-(define
-  rx-find-from
-  (fn
-    (compiled s search-start slen ci? mi?)
-    (if
-      (> search-start slen)
-      nil
-      (let
-        ((res (rx-try-at compiled s search-start slen ci? mi?)))
-        (if
-          res
-          res
-          (rx-find-from compiled s (+ search-start 1) slen ci? mi?))))))
-
-;; Build exec result dict from raw match result
-(define
-  rx-build-exec-result
-  (fn
-    (s match-res)
-    (let
-      ((start (get match-res "start"))
-        (end (get match-res "end"))
-        (groups (get match-res "groups"))
-        (ngroups (get match-res "ngroups")))
-      (let
-        ((matched (substring s start end))
-          (caps (rx-build-captures groups ngroups 1)))
-        (dict "match" matched "index" start "input" s "groups" caps)))))
-
-(define
-  rx-build-captures
-  (fn
-    (groups ngroups idx)
-    (if
-      (> idx ngroups)
-      (list)
-      (let
-        ((cap (get groups (js-to-string idx))))
-        (cons
-          (if (= cap nil) :js-undefined cap)
-          (rx-build-captures groups ngroups (+ idx 1)))))))
-
-;; ── Public interface ──────────────────────────────────────────────
-
-;; Lazy compile: build NFA on first use, cache under "__compiled__"
-(define
-  rx-ensure-compiled!
-  (fn
-    (rx)
-    (if
-      (dict-has? rx "__compiled__")
-      (get rx "__compiled__")
-      (let
-        ((c (rx-compile (get rx "source"))))
-        (begin (dict-set! rx "__compiled__" c) c)))))
-
-(define
-  rx-test
-  (fn
-    (rx s)
-    (let
-      ((compiled (rx-ensure-compiled! rx))
-        (ci? (get rx "ignoreCase"))
-        (mi? (get rx "multiline"))
-        (slen (len s)))
-      (let
-        ((start (if (get rx "global") (let ((li (get rx "lastIndex"))) (if (number? li) li 0)) 0)))
-        (let
-          ((res (rx-find-from compiled s start slen ci? mi?)))
-          (if
-            (get rx "global")
-            (begin
-              (dict-set! rx "lastIndex" (if res (get res "end") 0))
-              (if res true false))
-            (if res true false)))))))
-
-(define
-  rx-exec
-  (fn
-    (rx s)
-    (let
-      ((compiled (rx-ensure-compiled! rx))
-        (ci? (get rx "ignoreCase"))
-        (mi? (get rx "multiline"))
-        (slen (len s)))
-      (let
-        ((start (if (get rx "global") (let ((li (get rx "lastIndex"))) (if (number? li) li 0)) 0)))
-        (let
-          ((res (rx-find-from compiled s start slen ci? mi?)))
-          (if
-            res
-            (begin
-              (when
-                (get rx "global")
-                (dict-set! rx "lastIndex" (get res "end")))
-              (rx-build-exec-result s res))
-            (begin
-              (when (get rx "global") (dict-set! rx "lastIndex" 0))
-              nil)))))))
-
-;; match-all for String.prototype.matchAll
-(define
-  js-regex-match-all
-  (fn
-    (rx s)
-    (let
-      ((compiled (rx-ensure-compiled! rx))
-        (ci? (get rx "ignoreCase"))
-        (mi? (get rx "multiline"))
-        (slen (len s))
-        (results (list)))
-      (rx-match-all-loop compiled s 0 slen ci? mi? results))))
-
-(define
-  rx-match-all-loop
-  (fn
-    (compiled s i slen ci? mi? results)
-    (if
-      (> i slen)
-      results
-      (let
-        ((res (rx-find-from compiled s i slen ci? mi?)))
-        (if
-          res
-          (begin
-            (append! results (rx-build-exec-result s res))
-            (let
-              ((next (get res "end")))
-              (rx-match-all-loop
-                compiled
-                s
-                (if (= next i) (+ i 1) next)
-                slen
-                ci?
-                mi?
-                results)))
-          results)))))
-
-;; ── Install platform ──────────────────────────────────────────────
-
-(js-regex-platform-override! "test" rx-test)
-(js-regex-platform-override! "exec" rx-exec)

lib/js/runtime.sx

@@ -2032,15 +2032,7 @@
           (&rest args)
           (cond
             ((= (len args) 0) nil)
-            ((js-regex? (nth args 0))
+            ((js-regex? (nth args 0)) (js-regex-stub-exec (nth args 0) s))
-              (let
-                ((rx (nth args 0)))
-                (let
-                  ((impl (get __js_regex_platform__ "exec")))
-                  (if
-                    (js-undefined? impl)
-                    (js-regex-stub-exec rx s)
-                    (impl rx s)))))
             (else
               (let
                 ((needle (js-to-string (nth args 0))))
@@ -2049,7 +2041,7 @@
                   (if
                     (= idx -1)
                     nil
-                    (let ((res (list))) (begin (append! res needle) res)))))))))
+                    (let ((res (list))) (append! res needle) res))))))))
       ((= name "at")
         (fn
           (i)
@@ -2107,20 +2099,6 @@
       ((= name "toWellFormed") (fn () s))
       (else js-undefined))))
 
-(define __js_tdz_sentinel__ (dict "__tdz__" true))
-
-(define js-tdz? (fn (v) (and (dict? v) (dict-has? v "__tdz__"))))
-
-(define
-  js-tdz-check
-  (fn
-    (name val)
-    (if
-      (js-tdz? val)
-      (raise
-        (TypeError (str "Cannot access '" name "' before initialization")))
-      val)))
-
 (define
   js-string-slice
   (fn

lib/js/test.sh

@@ -33,8 +33,6 @@ cat > "$TMPFILE" << 'EPOCHS'
 (load "lib/js/transpile.sx")
 (epoch 5)
 (load "lib/js/runtime.sx")
-(epoch 6)
-(load "lib/js/regex.sx")
 
 ;; ── Phase 0: stubs still behave ─────────────────────────────────
 (epoch 10)
@@ -1325,108 +1323,6 @@ cat > "$TMPFILE" << 'EPOCHS'
 (epoch 3505)
 (eval "(js-eval \"var a = {length: 3, 0: 10, 1: 20, 2: 30}; var sum = 0; Array.prototype.forEach.call(a, function(x){sum += x;}); sum\")")
 
-;; ── Phase 12: Regex engine ────────────────────────────────────────
-;; Platform is installed (test key is a function, not undefined)
-(epoch 5000)
-(eval "(js-undefined? (get __js_regex_platform__ \"test\"))")
-(epoch 5001)
-(eval "(js-eval \"/foo/.test('hi foo bar')\")")
-(epoch 5002)
-(eval "(js-eval \"/foo/.test('hi bar')\")")
-;; Case-insensitive flag
-(epoch 5003)
-(eval "(js-eval \"/FOO/i.test('hello foo world')\")")
-;; Anchors
-(epoch 5004)
-(eval "(js-eval \"/^hello/.test('hello world')\")")
-(epoch 5005)
-(eval "(js-eval \"/^hello/.test('say hello')\")")
-(epoch 5006)
-(eval "(js-eval \"/world$/.test('hello world')\")")
-;; Character classes
-(epoch 5007)
-(eval "(js-eval \"/\\\\d+/.test('abc 123')\")")
-(epoch 5008)
-(eval "(js-eval \"/\\\\w+/.test('hello')\")")
-(epoch 5009)
-(eval "(js-eval \"/[abc]/.test('dog')\")")
-(epoch 5010)
-(eval "(js-eval \"/[abc]/.test('cat')\")")
-;; Quantifiers
-(epoch 5011)
-(eval "(js-eval \"/a*b/.test('b')\")")
-(epoch 5012)
-(eval "(js-eval \"/a+b/.test('b')\")")
-(epoch 5013)
-(eval "(js-eval \"/a{2,3}/.test('aa')\")")
-(epoch 5014)
-(eval "(js-eval \"/a{2,3}/.test('a')\")")
-;; Dot
-(epoch 5015)
-(eval "(js-eval \"/h.llo/.test('hello')\")")
-(epoch 5016)
-(eval "(js-eval \"/h.llo/.test('hllo')\")")
-;; exec result
-(epoch 5017)
-(eval "(js-eval \"var m = /foo(\\\\w+)/.exec('foobar'); m.match\")")
-(epoch 5018)
-(eval "(js-eval \"var m = /foo(\\\\w+)/.exec('foobar'); m.index\")")
-(epoch 5019)
-(eval "(js-eval \"var m = /foo(\\\\w+)/.exec('foobar'); m.groups[0]\")")
-;; Alternation
-(epoch 5020)
-(eval "(js-eval \"/cat|dog/.test('I have a dog')\")")
-(epoch 5021)
-(eval "(js-eval \"/cat|dog/.test('I have a fish')\")")
-;; Non-capturing group
-(epoch 5022)
-(eval "(js-eval \"/(?:foo)+/.test('foofoo')\")")
-;; Negated char class
-(epoch 5023)
-(eval "(js-eval \"/[^abc]/.test('d')\")")
-(epoch 5024)
-(eval "(js-eval \"/[^abc]/.test('a')\")")
-;; Range inside char class
-(epoch 5025)
-(eval "(js-eval \"/[a-z]+/.test('hello')\")")
-;; Word boundary
-(epoch 5026)
-(eval "(js-eval \"/\\\\bword\\\\b/.test('a word here')\")")
-(epoch 5027)
-(eval "(js-eval \"/\\\\bword\\\\b/.test('password')\")")
-;; Lazy quantifier
-(epoch 5028)
-(eval "(js-eval \"var m = /a+?/.exec('aaa'); m.match\")")
-;; Global flag exec
-(epoch 5029)
-(eval "(js-eval \"var r=/\\\\d+/g; r.exec('a1b2'); r.exec('a1b2').match\")")
-;; String.prototype.match with regex
-(epoch 5030)
-(eval "(js-eval \"'hello world'.match(/\\\\w+/).match\")")
-;; String.prototype.search
-(epoch 5031)
-(eval "(js-eval \"'hello world'.search(/world/)\")")
-;; String.prototype.replace with regex
-(epoch 5032)
-(eval "(js-eval \"'hello world'.replace(/world/, 'there')\")")
-;; multiline anchor
-(epoch 5033)
-(eval "(js-eval \"/^bar/m.test('foo\\nbar')\")")
-
-;; ── Phase 13: let/const TDZ infrastructure ───────────────────────
-;; The TDZ sentinel and checker are defined in runtime.sx.
-;; let/const bindings work normally after initialization.
-(epoch 5100)
-(eval "(js-eval \"let x = 5; x\")")
-(epoch 5101)
-(eval "(js-eval \"const y = 42; y\")")
-;; TDZ sentinel exists and is detectable
-(epoch 5102)
-(eval "(js-tdz? __js_tdz_sentinel__)")
-;; js-tdz-check passes through non-sentinel values
-(epoch 5103)
-(eval "(js-tdz-check \"x\" 42)")
-
 EPOCHS
 
 
@@ -2146,48 +2042,6 @@ check 3503 "indexOf.call arrLike"          '1'
 check 3504 "filter.call arrLike"           '"2,3"'
 check 3505 "forEach.call arrLike sum"      '60'
 
-# ── Phase 12: Regex engine ────────────────────────────────────────
-check 5000 "regex platform installed"           'false'
-check 5001 "/foo/ matches"                      'true'
-check 5002 "/foo/ no match"                     'false'
-check 5003 "/FOO/i case-insensitive"            'true'
-check 5004 "/^hello/ anchor match"              'true'
-check 5005 "/^hello/ anchor no-match"           'false'
-check 5006 "/world$/ end anchor"                'true'
-check 5007 "/\\d+/ digit class"                 'true'
-check 5008 "/\\w+/ word class"                  'true'
-check 5009 "/[abc]/ class no-match"             'false'
-check 5010 "/[abc]/ class match"                'true'
-check 5011 "/a*b/ zero-or-more"                 'true'
-check 5012 "/a+b/ one-or-more no-match"         'false'
-check 5013 "/a{2,3}/ quant match"               'true'
-check 5014 "/a{2,3}/ quant no-match"            'false'
-check 5015 "dot matches any"                    'true'
-check 5016 "dot requires char"                  'false'
-check 5017 "exec match string"                  '"foobar"'
-check 5018 "exec match index"                   '0'
-check 5019 "exec capture group"                 '"bar"'
-check 5020 "alternation cat|dog match"          'true'
-check 5021 "alternation cat|dog no-match"       'false'
-check 5022 "non-capturing group"                'true'
-check 5023 "negated class match"                'true'
-check 5024 "negated class no-match"             'false'
-check 5025 "range [a-z]+"                       'true'
-check 5026 "word boundary match"                'true'
-check 5027 "word boundary no-match"             'false'
-check 5028 "lazy quantifier"                    '"a"'
-check 5029 "global exec advances"               '"2"'
-check 5030 "String.match regex"                 '"hello"'
-check 5031 "String.search regex"                '6'
-check 5032 "String.replace regex"               '"hello there"'
-check 5033 "multiline anchor"                   'true'
-
-# ── Phase 13: let/const TDZ infrastructure ───────────────────────
-check 5100 "let binding initialized"            '5'
-check 5101 "const binding initialized"          '42'
-check 5102 "TDZ sentinel is detectable"         'true'
-check 5103 "tdz-check passes non-sentinel"      '42'
-
 TOTAL=$((PASS + FAIL))
 if [ $FAIL -eq 0 ]; then
   echo "✓ $PASS/$TOTAL JS-on-SX tests passed"

lib/js/test262-runner.py

@@ -798,7 +798,6 @@ class ServerSession:
         self._run_and_collect(3, '(load "lib/js/parser.sx")', timeout=60.0)
         self._run_and_collect(4, '(load "lib/js/transpile.sx")', timeout=60.0)
         self._run_and_collect(5, '(load "lib/js/runtime.sx")', timeout=60.0)
-        self._run_and_collect(50, '(load "lib/js/regex.sx")', timeout=60.0)
         # Preload the stub harness — use precomputed SX cache when available
         # (huge win: ~15s js-eval HARNESS_STUB → ~0s load precomputed .sx).
         cache_rel = _harness_cache_rel_path()

lib/js/transpile.sx

@@ -935,12 +935,12 @@
 
 (define
   js-transpile-var
-  (fn (kind decls) (cons (js-sym "begin") (js-vardecl-forms kind decls))))
+  (fn (kind decls) (cons (js-sym "begin") (js-vardecl-forms decls))))
 
 (define
   js-vardecl-forms
   (fn
-    (kind decls)
+    (decls)
     (cond
       ((empty? decls) (list))
       (else
@@ -953,7 +953,7 @@
                   (js-sym "define")
                   (js-sym (nth d 1))
                   (js-transpile (nth d 2)))
-                (js-vardecl-forms kind (rest decls))))
+                (js-vardecl-forms (rest decls))))
             ((js-tag? d "js-vardecl-obj")
               (let
                 ((names (nth d 1))
@@ -964,7 +964,7 @@
                   (js-vardecl-obj-forms
                     names
                     tmp-sym
-                    (js-vardecl-forms kind (rest decls))))))
+                    (js-vardecl-forms (rest decls))))))
             ((js-tag? d "js-vardecl-arr")
               (let
                 ((names (nth d 1))
@@ -976,7 +976,7 @@
                     names
                     tmp-sym
                     0
-                    (js-vardecl-forms kind (rest decls))))))
+                    (js-vardecl-forms (rest decls))))))
             (else (error "js-vardecl-forms: unexpected decl"))))))))
 
 (define

lib/tcl/parser.sx

@@ -0,0 +1,41 @@
+; Tcl parser — thin layer over tcl-tokenize
+; Adds tcl-parse entry point and word utility fns
+
+; Entry point: parse Tcl source to a list of commands.
+; Returns same structure as tcl-tokenize.
+(define tcl-parse (fn (src) (tcl-tokenize src)))
+
+; True if word has no substitutions — value can be read statically.
+; braced words are always simple. compound words are simple when all
+; parts are plain text with no var/cmd parts.
+(define tcl-word-simple?
+  (fn (word)
+    (cond
+      ((= (get word :type) "braced") true)
+      ((= (get word :type) "compound")
+        (let ((parts (get word :parts)))
+          (every? (fn (p) (= (get p :type) "text")) parts)))
+      (else false))))
+
+; Concatenate text parts of a simple word into a single string.
+; For braced words returns :value directly.
+; For compound words with only text parts, joins them.
+; Returns nil for words with substitutions.
+(define tcl-word-literal
+  (fn (word)
+    (cond
+      ((= (get word :type) "braced") (get word :value))
+      ((= (get word :type) "compound")
+        (if (tcl-word-simple? word)
+          (join "" (map (fn (p) (get p :value)) (get word :parts)))
+          nil))
+      (else nil))))
+
+; Number of words in a parsed command.
+(define tcl-cmd-len
+  (fn (cmd) (len (get cmd :words))))
+
+; Nth word literal from a command (index 0 = command name).
+; Returns nil if word has substitutions.
+(define tcl-nth-literal
+  (fn (cmd n) (tcl-word-literal (nth (get cmd :words) n))))

lib/tcl/test.sh

@@ -0,0 +1,53 @@
+#!/usr/bin/env bash
+# Tcl-on-SX test runner — epoch protocol to sx_server.exe
+set -uo pipefail
+cd "$(git rev-parse --show-toplevel)"
+
+SX_SERVER="${SX_SERVER:-hosts/ocaml/_build/default/bin/sx_server.exe}"
+if [ ! -x "$SX_SERVER" ]; then
+  SX_SERVER="/root/rose-ash/hosts/ocaml/_build/default/bin/sx_server.exe"
+fi
+if [ ! -x "$SX_SERVER" ]; then echo "ERROR: sx_server.exe not found"; exit 1; fi
+
+VERBOSE="${1:-}"
+TMPFILE=$(mktemp)
+trap "rm -f $TMPFILE" EXIT
+
+cat > "$TMPFILE" << 'EPOCHS'
+(epoch 1)
+(load "lib/tcl/tokenizer.sx")
+(epoch 2)
+(load "lib/tcl/parser.sx")
+(epoch 3)
+(load "lib/tcl/tests/parse.sx")
+(epoch 4)
+(eval "(tcl-run-parse-tests)")
+EPOCHS
+
+OUTPUT=$(timeout 30 "$SX_SERVER" < "$TMPFILE" 2>&1)
+[ "$VERBOSE" = "-v" ] && echo "$OUTPUT"
+
+# Result follows an (ok-len 3 N) line
+RESULT=$(echo "$OUTPUT" | grep -A1 "^(ok-len 4 " | tail -1)
+if [ -z "$RESULT" ]; then
+  RESULT=$(echo "$OUTPUT" | grep "^(ok 4 " | sed 's/^(ok 3 //' | sed 's/)$//')
+fi
+if [ -z "$RESULT" ]; then
+  echo "ERROR: no result from epoch 4"
+  echo "$OUTPUT" | tail -10
+  exit 1
+fi
+
+PASSED=$(echo "$RESULT" | grep -o ':passed [0-9]*' | grep -o '[0-9]*$')
+FAILED=$(echo "$RESULT" | grep -o ':failed [0-9]*' | grep -o '[0-9]*$')
+PASSED=${PASSED:-0}; FAILED=${FAILED:-1}
+TOTAL=$((PASSED + FAILED))
+
+if [ "$FAILED" = "0" ]; then
+  echo "ok $PASSED/$TOTAL tcl-tokenize tests passed"
+  exit 0
+else
+  echo "FAIL $PASSED/$TOTAL passed, $FAILED failed"
+  echo "$RESULT"
+  exit 1
+fi

lib/tcl/tests/parse.sx

@@ -0,0 +1,186 @@
+(define tcl-parse-pass 0)
+(define tcl-parse-fail 0)
+(define tcl-parse-failures (list))
+
+(define tcl-assert
+  (fn (label expected actual)
+    (if (= expected actual)
+      (set! tcl-parse-pass (+ tcl-parse-pass 1))
+      (begin
+        (set! tcl-parse-fail (+ tcl-parse-fail 1))
+        (append! tcl-parse-failures
+          (str label ": expected=" (str expected) " got=" (str actual)))))))
+
+(define tcl-first-cmd
+  (fn (src) (nth (tcl-tokenize src) 0)))
+
+(define tcl-cmd-words
+  (fn (src) (get (tcl-first-cmd src) :words)))
+
+(define tcl-word
+  (fn (src wi) (nth (tcl-cmd-words src) wi)))
+
+(define tcl-parts
+  (fn (src wi) (get (tcl-word src wi) :parts)))
+
+(define tcl-part
+  (fn (src wi pi) (nth (tcl-parts src wi) pi)))
+
+(define tcl-run-parse-tests
+  (fn ()
+    (set! tcl-parse-pass 0)
+    (set! tcl-parse-fail 0)
+    (set! tcl-parse-failures (list))
+
+    ; empty / whitespace-only
+    (tcl-assert "empty" 0 (len (tcl-tokenize "")))
+    (tcl-assert "ws-only" 0 (len (tcl-tokenize "   ")))
+    (tcl-assert "nl-only" 0 (len (tcl-tokenize "\n\n")))
+
+    ; single command word count
+    (tcl-assert "1word" 1 (len (tcl-cmd-words "set")))
+    (tcl-assert "3words" 3 (len (tcl-cmd-words "set x 1")))
+    (tcl-assert "4words" 4 (len (tcl-cmd-words "set a b c")))
+
+    ; word type — bare word is compound
+    (tcl-assert "bare-type" "compound" (get (tcl-word "set x 1" 0) :type))
+    (tcl-assert "bare-quoted" false (get (tcl-word "set x 1" 0) :quoted))
+    (tcl-assert "bare-part-type" "text" (get (tcl-part "set x 1" 0 0) :type))
+    (tcl-assert "bare-part-val" "set" (get (tcl-part "set x 1" 0 0) :value))
+    (tcl-assert "bare-part2-val" "x" (get (tcl-part "set x 1" 1 0) :value))
+    (tcl-assert "bare-part3-val" "1" (get (tcl-part "set x 1" 2 0) :value))
+
+    ; multiple commands
+    (tcl-assert "semi-sep" 2 (len (tcl-tokenize "set x 1; set y 2")))
+    (tcl-assert "nl-sep" 2 (len (tcl-tokenize "set x 1\nset y 2")))
+    (tcl-assert "multi-nl" 3 (len (tcl-tokenize "a\nb\nc")))
+
+    ; comments
+    (tcl-assert "comment-only" 0 (len (tcl-tokenize "# comment")))
+    (tcl-assert "comment-nl" 0 (len (tcl-tokenize "# comment\n")))
+    (tcl-assert "comment-then-cmd" 1 (len (tcl-tokenize "# comment\nset x 1")))
+    (tcl-assert "semi-then-comment" 1 (len (tcl-tokenize "set x 1; # comment")))
+
+    ; brace-quoted words
+    (tcl-assert "brace-type" "braced" (get (tcl-word "{hello}" 0) :type))
+    (tcl-assert "brace-value" "hello" (get (tcl-word "{hello}" 0) :value))
+    (tcl-assert "brace-spaces" "hello world" (get (tcl-word "{hello world}" 0) :value))
+    (tcl-assert "brace-nested" "a {b} c" (get (tcl-word "{a {b} c}" 0) :value))
+    (tcl-assert "brace-no-var-sub" "hello $x" (get (tcl-word "{hello $x}" 0) :value))
+    (tcl-assert "brace-no-cmd-sub" "[expr 1]" (get (tcl-word "{[expr 1]}" 0) :value))
+
+    ; double-quoted words
+    (tcl-assert "dq-type" "compound" (get (tcl-word "\"hello\"" 0) :type))
+    (tcl-assert "dq-quoted" true (get (tcl-word "\"hello\"" 0) :quoted))
+    (tcl-assert "dq-literal" "hello" (get (tcl-part "\"hello\"" 0 0) :value))
+
+    ; variable substitution in bare word
+    (tcl-assert "var-type" "var" (get (tcl-part "$x" 0 0) :type))
+    (tcl-assert "var-name" "x" (get (tcl-part "$x" 0 0) :name))
+    (tcl-assert "var-long" "long_name" (get (tcl-part "$long_name" 0 0) :name))
+
+    ; ${name} form
+    (tcl-assert "var-brace-type" "var" (get (tcl-part "${x}" 0 0) :type))
+    (tcl-assert "var-brace-name" "x" (get (tcl-part "${x}" 0 0) :name))
+
+    ; array variable substitution
+    (tcl-assert "arr-type" "var-arr" (get (tcl-part "$arr(key)" 0 0) :type))
+    (tcl-assert "arr-name" "arr" (get (tcl-part "$arr(key)" 0 0) :name))
+    (tcl-assert "arr-key-len" 1 (len (get (tcl-part "$arr(key)" 0 0) :key)))
+    (tcl-assert "arr-key-text" "key"
+      (get (nth (get (tcl-part "$arr(key)" 0 0) :key) 0) :value))
+
+    ; command substitution
+    (tcl-assert "cmd-type" "cmd" (get (tcl-part "[expr 1+1]" 0 0) :type))
+    (tcl-assert "cmd-src" "expr 1+1" (get (tcl-part "[expr 1+1]" 0 0) :src))
+
+    ; nested command substitution
+    (tcl-assert "cmd-nested-src" "expr [string length x]"
+      (get (tcl-part "[expr [string length x]]" 0 0) :src))
+
+    ; backslash substitution in double-quoted word
+    (let ((ps (tcl-parts "\"a\\nb\"" 0)))
+      (begin
+        (tcl-assert "bs-n-part0" "a" (get (nth ps 0) :value))
+        (tcl-assert "bs-n-part1" "\n" (get (nth ps 1) :value))
+        (tcl-assert "bs-n-part2" "b" (get (nth ps 2) :value))))
+
+    (let ((ps (tcl-parts "\"a\\tb\"" 0)))
+      (tcl-assert "bs-t-part1" "\t" (get (nth ps 1) :value)))
+
+    (let ((ps (tcl-parts "\"a\\\\b\"" 0)))
+      (tcl-assert "bs-bs-part1" "\\" (get (nth ps 1) :value)))
+
+    ; mixed word: text + var + text in double-quoted
+    (let ((ps (tcl-parts "\"hello $name!\"" 0)))
+      (begin
+        (tcl-assert "mixed-text0" "hello " (get (nth ps 0) :value))
+        (tcl-assert "mixed-var1-type" "var" (get (nth ps 1) :type))
+        (tcl-assert "mixed-var1-name" "name" (get (nth ps 1) :name))
+        (tcl-assert "mixed-text2" "!" (get (nth ps 2) :value))))
+
+    ; {*} expansion
+    (tcl-assert "expand-type" "expand" (get (tcl-word "{*}$list" 0) :type))
+
+    ; line continuation between words
+    (tcl-assert "cont-words" 3 (len (tcl-cmd-words "set x \\\n  1")))
+
+    ; continuation — third command word is correct
+    (tcl-assert "cont-word2-val" "1"
+      (get (tcl-part "set x \\\n  1" 2 0) :value))
+
+
+    ; --- parser helpers ---
+    ; tcl-parse is an alias for tcl-tokenize
+    (tcl-assert "parse-cmd-count" 1 (len (tcl-parse "set x 1")))
+    (tcl-assert "parse-2cmds" 2 (len (tcl-parse "set x 1; set y 2")))
+
+    ; tcl-cmd-len
+    (tcl-assert "cmd-len-3" 3 (tcl-cmd-len (nth (tcl-parse "set x 1") 0)))
+    (tcl-assert "cmd-len-1" 1 (tcl-cmd-len (nth (tcl-parse "puts") 0)))
+
+    ; tcl-word-simple? on braced word
+    (tcl-assert "simple-braced" true
+      (tcl-word-simple? (nth (get (nth (tcl-parse "{hello}") 0) :words) 0)))
+
+    ; tcl-word-simple? on bare word with no subs
+    (tcl-assert "simple-bare" true
+      (tcl-word-simple? (nth (get (nth (tcl-parse "hello") 0) :words) 0)))
+
+    ; tcl-word-simple? on word containing a var sub — false
+    (tcl-assert "simple-var-false" false
+      (tcl-word-simple? (nth (get (nth (tcl-parse "$x") 0) :words) 0)))
+
+    ; tcl-word-simple? on word containing a cmd sub — false
+    (tcl-assert "simple-cmd-false" false
+      (tcl-word-simple? (nth (get (nth (tcl-parse "[expr 1]") 0) :words) 0)))
+
+    ; tcl-word-literal on braced word
+    (tcl-assert "lit-braced" "hello world"
+      (tcl-word-literal (nth (get (nth (tcl-parse "{hello world}") 0) :words) 0)))
+
+    ; tcl-word-literal on bare word
+    (tcl-assert "lit-bare" "hello"
+      (tcl-word-literal (nth (get (nth (tcl-parse "hello") 0) :words) 0)))
+
+    ; tcl-word-literal on word with var sub returns nil
+    (tcl-assert "lit-var-nil" nil
+      (tcl-word-literal (nth (get (nth (tcl-parse "$x") 0) :words) 0)))
+
+    ; tcl-nth-literal
+    (tcl-assert "nth-lit-0" "set"
+      (tcl-nth-literal (nth (tcl-parse "set x 1") 0) 0))
+    (tcl-assert "nth-lit-1" "x"
+      (tcl-nth-literal (nth (tcl-parse "set x 1") 0) 1))
+    (tcl-assert "nth-lit-2" "1"
+      (tcl-nth-literal (nth (tcl-parse "set x 1") 0) 2))
+
+    ; tcl-nth-literal returns nil when word has subs
+    (tcl-assert "nth-lit-nil" nil
+      (tcl-nth-literal (nth (tcl-parse "set x $y") 0) 2))
+
+
+    (dict
+      "passed" tcl-parse-pass
+      "failed" tcl-parse-fail
+      "failures" tcl-parse-failures)))

lib/tcl/tokenizer.sx

@@ -0,0 +1,308 @@
+(define tcl-ws? (fn (c) (or (= c " ") (= c "\t") (= c "\r"))))
+
+(define tcl-alpha?
+  (fn (c)
+    (and
+      (not (= c nil))
+      (or (and (>= c "a") (<= c "z")) (and (>= c "A") (<= c "Z"))))))
+
+(define tcl-digit?
+  (fn (c) (and (not (= c nil)) (>= c "0") (<= c "9"))))
+
+(define tcl-ident-start?
+  (fn (c) (or (tcl-alpha? c) (= c "_"))))
+
+(define tcl-ident-char?
+  (fn (c) (or (tcl-ident-start? c) (tcl-digit? c))))
+
+(define tcl-tokenize
+  (fn (src)
+    (let ((pos 0) (src-len (len src)) (commands (list)))
+
+      (define char-at
+        (fn (off)
+          (if (< (+ pos off) src-len) (nth src (+ pos off)) nil)))
+
+      (define cur (fn () (char-at 0)))
+
+      (define advance! (fn (n) (set! pos (+ pos n))))
+
+      (define skip-ws!
+        (fn ()
+          (when (tcl-ws? (cur))
+            (begin (advance! 1) (skip-ws!)))))
+
+      (define skip-to-eol!
+        (fn ()
+          (when (and (< pos src-len) (not (= (cur) "\n")))
+            (begin (advance! 1) (skip-to-eol!)))))
+
+      (define skip-brace-content!
+        (fn (d)
+          (when (and (< pos src-len) (> d 0))
+            (cond
+              ((= (cur) "{") (begin (advance! 1) (skip-brace-content! (+ d 1))))
+              ((= (cur) "}") (begin (advance! 1) (skip-brace-content! (- d 1))))
+              (else (begin (advance! 1) (skip-brace-content! d)))))))
+
+      (define skip-dquote-content!
+        (fn ()
+          (when (and (< pos src-len) (not (= (cur) "\"")))
+            (begin
+              (when (= (cur) "\\") (advance! 1))
+              (when (< pos src-len) (advance! 1))
+              (skip-dquote-content!)))))
+
+      (define parse-bs
+        (fn ()
+          (advance! 1)
+          (let ((c (cur)))
+            (cond
+              ((= c nil)  "\\")
+              ((= c "n")  (begin (advance! 1) "\n"))
+              ((= c "t")  (begin (advance! 1) "\t"))
+              ((= c "r")  (begin (advance! 1) "\r"))
+              ((= c "\\") (begin (advance! 1) "\\"))
+              ((= c "[")  (begin (advance! 1) "["))
+              ((= c "]")  (begin (advance! 1) "]"))
+              ((= c "{")  (begin (advance! 1) "{"))
+              ((= c "}")  (begin (advance! 1) "}"))
+              ((= c "$")  (begin (advance! 1) "$"))
+              ((= c ";")  (begin (advance! 1) ";"))
+              ((= c "\"") (begin (advance! 1) "\""))
+              ((= c "'")  (begin (advance! 1) "'"))
+              ((= c " ")  (begin (advance! 1) " "))
+              ((= c "\n")
+                (begin
+                  (advance! 1)
+                  (skip-ws!)
+                  " "))
+              (else (begin (advance! 1) (str "\\" c)))))))
+
+      (define parse-cmd-sub
+        (fn ()
+          (advance! 1)
+          (let ((start pos) (depth 1))
+            (define scan!
+              (fn ()
+                (when (and (< pos src-len) (> depth 0))
+                  (cond
+                    ((= (cur) "[")
+                      (begin (set! depth (+ depth 1)) (advance! 1) (scan!)))
+                    ((= (cur) "]")
+                      (begin
+                        (set! depth (- depth 1))
+                        (when (> depth 0) (advance! 1))
+                        (scan!)))
+                    ((= (cur) "{")
+                      (begin (advance! 1) (skip-brace-content! 1) (scan!)))
+                    ((= (cur) "\"")
+                      (begin
+                        (advance! 1)
+                        (skip-dquote-content!)
+                        (when (= (cur) "\"") (advance! 1))
+                        (scan!)))
+                    ((= (cur) "\\")
+                      (begin (advance! 1) (when (< pos src-len) (advance! 1)) (scan!)))
+                    (else (begin (advance! 1) (scan!)))))))
+            (scan!)
+            (let ((src-text (slice src start pos)))
+              (begin
+                (when (= (cur) "]") (advance! 1))
+                {:type "cmd" :src src-text})))))
+
+      (define scan-name!
+        (fn ()
+          (when (and (< pos src-len) (not (= (cur) "}")))
+            (begin (advance! 1) (scan-name!)))))
+
+      (define scan-ns-name!
+        (fn ()
+          (cond
+            ((tcl-ident-char? (cur))
+              (begin (advance! 1) (scan-ns-name!)))
+            ((and (= (cur) ":") (= (char-at 1) ":"))
+              (begin (advance! 2) (scan-ns-name!)))
+            (else nil))))
+
+      (define scan-klit!
+        (fn ()
+          (when (and (< pos src-len)
+                     (not (= (cur) ")"))
+                     (not (= (cur) "$"))
+                     (not (= (cur) "["))
+                     (not (= (cur) "\\")))
+            (begin (advance! 1) (scan-klit!)))))
+
+      (define scan-key!
+        (fn (kp)
+          (when (and (< pos src-len) (not (= (cur) ")")))
+            (cond
+              ((= (cur) "$")
+                (begin (append! kp (parse-var-sub)) (scan-key! kp)))
+              ((= (cur) "[")
+                (begin (append! kp (parse-cmd-sub)) (scan-key! kp)))
+              ((= (cur) "\\")
+                (begin
+                  (append! kp {:type "text" :value (parse-bs)})
+                  (scan-key! kp)))
+              (else
+                (let ((kstart pos))
+                  (begin
+                    (scan-klit!)
+                    (append! kp {:type "text" :value (slice src kstart pos)})
+                    (scan-key! kp))))))))
+
+      (define parse-var-sub
+        (fn ()
+          (advance! 1)
+          (cond
+            ((= (cur) "{")
+              (begin
+                (advance! 1)
+                (let ((start pos))
+                  (begin
+                    (scan-name!)
+                    (let ((name (slice src start pos)))
+                      (begin
+                        (when (= (cur) "}") (advance! 1))
+                        {:type "var" :name name}))))))
+            ((tcl-ident-start? (cur))
+              (let ((start pos))
+                (begin
+                  (scan-ns-name!)
+                  (let ((name (slice src start pos)))
+                    (if (= (cur) "(")
+                      (begin
+                        (advance! 1)
+                        (let ((key-parts (list)))
+                          (begin
+                            (scan-key! key-parts)
+                            (when (= (cur) ")") (advance! 1))
+                            {:type "var-arr" :name name :key key-parts})))
+                      {:type "var" :name name})))))
+            (else {:type "text" :value "$"}))))
+
+      (define scan-lit!
+        (fn (stop?)
+          (when (and (< pos src-len)
+                     (not (stop? (cur)))
+                     (not (= (cur) "$"))
+                     (not (= (cur) "["))
+                     (not (= (cur) "\\")))
+            (begin (advance! 1) (scan-lit! stop?)))))
+
+      (define parse-word-parts!
+        (fn (parts stop?)
+          (when (and (< pos src-len) (not (stop? (cur))))
+            (cond
+              ((= (cur) "$")
+                (begin (append! parts (parse-var-sub)) (parse-word-parts! parts stop?)))
+              ((= (cur) "[")
+                (begin (append! parts (parse-cmd-sub)) (parse-word-parts! parts stop?)))
+              ((= (cur) "\\")
+                (begin
+                  (append! parts {:type "text" :value (parse-bs)})
+                  (parse-word-parts! parts stop?)))
+              (else
+                (let ((start pos))
+                  (begin
+                    (scan-lit! stop?)
+                    (when (> pos start)
+                      (append! parts {:type "text" :value (slice src start pos)}))
+                    (parse-word-parts! parts stop?))))))))
+
+      (define parse-brace-word
+        (fn ()
+          (advance! 1)
+          (let ((depth 1) (start pos))
+            (define scan!
+              (fn ()
+                (when (and (< pos src-len) (> depth 0))
+                  (cond
+                    ((= (cur) "{")
+                      (begin (set! depth (+ depth 1)) (advance! 1) (scan!)))
+                    ((= (cur) "}")
+                      (begin (set! depth (- depth 1)) (when (> depth 0) (advance! 1)) (scan!)))
+                    (else (begin (advance! 1) (scan!)))))))
+            (scan!)
+            (let ((value (slice src start pos)))
+              (begin
+                (when (= (cur) "}") (advance! 1))
+                {:type "braced" :value value})))))
+
+      (define parse-dquote-word
+        (fn ()
+          (advance! 1)
+          (let ((parts (list)))
+            (begin
+              (parse-word-parts! parts (fn (c) (or (= c "\"") (= c nil))))
+              (when (= (cur) "\"") (advance! 1))
+              {:type "compound" :parts parts :quoted true}))))
+
+      (define parse-bare-word
+        (fn ()
+          (let ((parts (list)))
+            (begin
+              (parse-word-parts!
+                parts
+                (fn (c) (or (tcl-ws? c) (= c "\n") (= c ";") (= c nil))))
+              {:type "compound" :parts parts :quoted false}))))
+
+      (define parse-word-no-expand
+        (fn ()
+          (cond
+            ((= (cur) "{") (parse-brace-word))
+            ((= (cur) "\"") (parse-dquote-word))
+            (else (parse-bare-word)))))
+
+      (define parse-word
+        (fn ()
+          (cond
+            ((and (= (cur) "{") (= (char-at 1) "*") (= (char-at 2) "}"))
+              (begin
+                (advance! 3)
+                {:type "expand" :word (parse-word-no-expand)}))
+            ((= (cur) "{") (parse-brace-word))
+            ((= (cur) "\"") (parse-dquote-word))
+            (else (parse-bare-word)))))
+
+      (define parse-words!
+        (fn (words)
+          (skip-ws!)
+          (cond
+            ((or (= (cur) nil) (= (cur) "\n") (= (cur) ";")) nil)
+            ((and (= (cur) "\\") (= (char-at 1) "\n"))
+              (begin (advance! 2) (skip-ws!) (parse-words! words)))
+            (else
+              (begin
+                (append! words (parse-word))
+                (parse-words! words))))))
+
+      (define skip-seps!
+        (fn ()
+          (when (< pos src-len)
+            (cond
+              ((or (tcl-ws? (cur)) (= (cur) "\n") (= (cur) ";"))
+                (begin (advance! 1) (skip-seps!)))
+              ((and (= (cur) "\\") (= (char-at 1) "\n"))
+                (begin (advance! 2) (skip-seps!)))
+              (else nil)))))
+
+      (define parse-all!
+        (fn ()
+          (skip-seps!)
+          (when (< pos src-len)
+            (cond
+              ((= (cur) "#")
+                (begin (skip-to-eol!) (parse-all!)))
+              (else
+                (let ((words (list)))
+                  (begin
+                    (parse-words! words)
+                    (when (> (len words) 0)
+                      (append! commands {:type "command" :words words}))
+                    (parse-all!))))))))
+
+      (parse-all!)
+      commands)))

plans/js-on-sx.md

@@ -125,7 +125,7 @@ Each item: implement → tests → update progress. Mark `[x]` when tests green.
 - [x] Rest params (`...rest` → `&rest`)
 - [x] Default parameters (desugar to `if (param === undefined) param = default`)
 - [ ] `var` hoisting (deferred — treated as `let` for now)
-- [x] `let`/`const` TDZ — sentinel infrastructure (`__js_tdz_sentinel__`, `js-tdz?`, `js-tdz-check` in runtime.sx)
+- [ ] `let`/`const` TDZ (deferred)
 
 ### Phase 8 — Objects, prototypes, `this`
 - [x] Property descriptors (simplified — plain-dict `__proto__` chain, `js-set-prop` mutates)
@@ -241,8 +241,6 @@ Append-only record of completed iterations. Loop writes one line per iteration:
   - 29× Timeout (slow string/regex loops)
   - 16× ReferenceError — still some missing globals
 
-- 2026-04-25 — **Regex engine (lib/js/regex.sx) + let/const TDZ infrastructure.** New file `lib/js/regex.sx`: 39-form pure-SX recursive backtracking engine installed via `js-regex-platform-override!`. Covers literals, `.`, `\d\w\s` + negations, `[abc]/[^abc]/[a-z]` char classes, `^\$\b\B` anchors, greedy+lazy quantifiers (`* + ? {n,m} *? +? ??`), capturing groups, non-capturing `(?:...)`, alternation `a|b`, flags `i`/`g`/`m`. Groups: match inner first → set capture → match rest (correct boundary), avoids including rest-nodes content in capture. Greedy: expand-first then backtrack (correct longest-match semantics). `js-regex-match-all` for String.matchAll. Fixed `String.prototype.match` to use platform engine (was calling stub). TDZ infrastructure added to `runtime.sx`: `__js_tdz_sentinel__` (unique sentinel dict), `js-tdz?`, `js-tdz-check`. `transpile.sx` passes `kind` through `js-transpile-var → js-vardecl-forms` (no behavioral change yet — infrastructure ready). `test262-runner.py` and `conformance.sh` updated to load `regex.sx` as epoch 6/50. Unit: **559/560** (was 522/522 before regex tests added, now +38 new tests; 1 pre-existing backtick failure). Conformance: **148/148** (unchanged). Gotchas: (1) `sx_insert_near` on a pattern inside a top-level function body inserts there (not at top level) — need to use `sx_insert_near` on a top-level symbol name. (2) Greedy quantifier must expand-first before trying rest-nodes; the naive "try rest at each step" produces lazy behavior. (3) Capturing groups must match inner nodes in isolation first (to get the group's end position) then match rest — appending inner+rest-nodes would include rest in the capture string.
-
 ## Phase 3-5 gotchas
 
 Worth remembering for later phases:
@@ -261,7 +259,17 @@ Anything that would require a change outside `lib/js/` goes here with a minimal
 
 - **Pending-Promise await** — our `js-await-value` drains microtasks and unwraps *settled* Promises; it cannot truly suspend a JS fiber and resume later. Every Promise that settles eventually through the synchronous `resolve`/`reject` + microtask path works. A Promise that never settles without external input (e.g. a real `setTimeout` waiting on the event loop) would hit the `"await on pending Promise (no scheduler)"` error. Proper async suspension would need the JS eval path to run under `cek-step-loop` (not `eval-expr` → `cek-run`) and treat `await pending-Promise` as a `perform` that registers a resume thunk on the Promise's callback list. Non-trivial plumbing; out of scope for this phase. Consider it a Phase 9.5 item.
 
-- ~~**Regex platform primitives**~~ **RESOLVED** — `lib/js/regex.sx` ships a pure-SX recursive backtracking engine. Installs via `js-regex-platform-override!` at load. Covers: literals, `.`, `\d\w\s` and negations, `[abc]` / `[^abc]` / ranges, `^` `$` `\b \B`, `* + ? {n,m}` (greedy + lazy), capturing + non-capturing groups, alternation `a|b`, flags `i` (case-insensitive), `g` (global, advances lastIndex), `m` (multiline anchors). `js-regex-match-all` for String.matchAll. String.prototype.match regex path updated to use platform engine (was calling stub). 34 new unit tests added (5000–5033). Conformance: 148/148 (unchanged — slice had no regex fixtures).
+- **Regex platform primitives** — runtime ships a substring-based stub (`js-regex-stub-test` / `-exec`). Overridable via `js-regex-platform-override!` so a real engine can be dropped in. Required platform-primitive surface:
+  - `regex-compile pattern flags` — build an opaque compiled handle
+  - `regex-test compiled s` → bool
+  - `regex-exec compiled s` → match dict `{match index input groups}` or nil
+  - `regex-match-all compiled s` → list of match dicts (or empty list)
+  - `regex-replace compiled s replacement` → string
+  - `regex-replace-fn compiled s fn` → string (fn receives match+groups, returns string)
+  - `regex-split compiled s` → list of strings
+  - `regex-source compiled` → string
+  - `regex-flags compiled` → string
+  Ideally a single `(js-regex-platform-install-all! platform)` entry point the host calls once at boot. OCaml would wrap `Str` / `Re` or a dedicated regex lib; JS host can just delegate to the native `RegExp`.
 
 - **Math trig + transcendental primitives missing.** The scoreboard shows 34× "TypeError: not a function" across the Math category — every one a test calling `Math.sin/cos/tan/log/…` on our runtime. We shim `Math` via `js-global`; the SX runtime supplies `sqrt`, `pow`, `abs`, `floor`, `ceil`, `round` and a hand-rolled `trunc`/`sign`/`cbrt`/`hypot`. Nothing else. Missing platform primitives (each is a one-line OCaml/JS binding, but a primitive all the same — we can't land approximation polynomials from inside the JS shim, they'd blow `Math.sin(1e308)` precision):
   - Trig: `sin`, `cos`, `tan`, `asin`, `acos`, `atan`, `atan2`

plans/tcl-on-sx.md

@@ -50,7 +50,7 @@ Core mapping:
 ## Roadmap
 
 ### Phase 1 — tokenizer + parser (the Dodekalogue)
-- [ ] Tokenizer applying the 12 rules:
+- [x] Tokenizer applying the 12 rules:
   1. Commands separated by `;` or newlines
   2. Words separated by whitespace within a command
   3. Double-quoted words: `\` escapes + `[…]` + `${…}` + `$var` substitution
@@ -63,8 +63,8 @@ Core mapping:
   10. Order of substitution is left-to-right, single-pass
   11. Substitutions don't recurse — substituted text is not re-parsed
   12. The result of any substitution is the value, not a new script
-- [ ] Parser: script = list of commands; command = list of words; word = literal string + list of substitutions
+- [x] Parser: script = list of commands; command = list of words; word = literal string + list of substitutions
-- [ ] Unit tests in `lib/tcl/tests/parse.sx`
+- [x] Unit tests in `lib/tcl/tests/parse.sx`
 
 ### Phase 2 — sequential eval + core commands
 - [ ] `tcl-eval-script`: walk command list, dispatch each first-word into command table
@@ -120,7 +120,8 @@ Core mapping:
 
 _Newest first._
 
-- _(none yet)_
+- 2026-04-25: Phase 1 parser — `lib/tcl/parser.sx`, word-simple?/word-literal helpers, 67 tests green, commit 6ee05259
+- 2026-04-25: Phase 1 tokenizer (Dodekalogue) — `lib/tcl/tokenizer.sx`, 52 tests green, commit 666e29d5
 
 ## Blockers