From ae94a24de55d5438f2a50b1d9fde2738912735eb Mon Sep 17 00:00:00 2001
From: giles <giles.bradshaw@rose-ash.com>
Date: Sat, 25 Apr 2026 07:54:48 +0000
Subject: [PATCH] smalltalk: conformance.sh + scoreboard.{json,md}

---
 lib/smalltalk/conformance.sh  | 99 +++++++++++++++++++++++++++++++++++
 lib/smalltalk/scoreboard.json | 15 ++++++
 lib/smalltalk/scoreboard.md   | 44 ++++++++++++++++
 plans/smalltalk-on-sx.md      |  3 +-
 4 files changed, 160 insertions(+), 1 deletion(-)
 create mode 100755 lib/smalltalk/conformance.sh
 create mode 100644 lib/smalltalk/scoreboard.json
 create mode 100644 lib/smalltalk/scoreboard.md

diff --git a/lib/smalltalk/conformance.sh b/lib/smalltalk/conformance.sh
new file mode 100755
index 00000000..f7253548
--- /dev/null
+++ b/lib/smalltalk/conformance.sh
@@ -0,0 +1,99 @@
+#!/usr/bin/env bash
+# Smalltalk-on-SX conformance runner.
+#
+# Runs the full test suite once with per-file detail, pulls out the
+# classic-corpus numbers, and writes:
+#   lib/smalltalk/scoreboard.json   — machine-readable summary
+#   lib/smalltalk/scoreboard.md     — human-readable summary
+#
+# Usage: bash lib/smalltalk/conformance.sh
+
+set -uo pipefail
+cd "$(git rev-parse --show-toplevel)"
+
+OUT_JSON="lib/smalltalk/scoreboard.json"
+OUT_MD="lib/smalltalk/scoreboard.md"
+
+DATE=$(date -u +%Y-%m-%dT%H:%M:%SZ)
+
+# Catalog .st programs in the corpus.
+PROGRAMS=()
+for f in lib/smalltalk/tests/programs/*.st; do
+  [ -f "$f" ] || continue
+  PROGRAMS+=("$(basename "$f" .st)")
+done
+NUM_PROGRAMS=${#PROGRAMS[@]}
+
+# Run the full test suite with per-file detail.
+RUNNER_OUT=$(bash lib/smalltalk/test.sh -v 2>&1)
+RC=$?
+
+# Final summary line: "OK 403/403 ..." or "FAIL 400/403 ...".
+ALL_SUM=$(echo "$RUNNER_OUT" | grep -E '^(OK|FAIL) [0-9]+/[0-9]+' | tail -1)
+ALL_PASS=$(echo "$ALL_SUM" | grep -oE '[0-9]+/[0-9]+' | head -1 | cut -d/ -f1)
+ALL_TOTAL=$(echo "$ALL_SUM" | grep -oE '[0-9]+/[0-9]+' | head -1 | cut -d/ -f2)
+
+# Per-file pass counts (verbose lines look like "OK <path>  N passed").
+get_pass () {
+  local fname="$1"
+  echo "$RUNNER_OUT" | awk -v f="$fname" '
+    $0 ~ f { for (i=1; i<=NF; i++) if ($i ~ /^[0-9]+$/) { print $i; exit } }'
+}
+
+PROG_PASS=$(get_pass "tests/programs.sx")
+PROG_PASS=${PROG_PASS:-0}
+
+# scoreboard.json
+{
+  printf '{\n'
+  printf '  "date": "%s",\n' "$DATE"
+  printf '  "programs": [\n'
+  for i in "${!PROGRAMS[@]}"; do
+    sep=","; [ "$i" -eq "$((NUM_PROGRAMS - 1))" ] && sep=""
+    printf '    "%s.st"%s\n' "${PROGRAMS[$i]}" "$sep"
+  done
+  printf '  ],\n'
+  printf '  "program_count": %d,\n' "$NUM_PROGRAMS"
+  printf '  "program_tests_passed": %s,\n' "$PROG_PASS"
+  printf '  "all_tests_passed": %s,\n' "$ALL_PASS"
+  printf '  "all_tests_total": %s,\n' "$ALL_TOTAL"
+  printf '  "exit_code": %d\n' "$RC"
+  printf '}\n'
+} > "$OUT_JSON"
+
+# scoreboard.md
+{
+  printf '# Smalltalk-on-SX Scoreboard\n\n'
+  printf '_Last run: %s_\n\n' "$DATE"
+
+  printf '## Totals\n\n'
+  printf '| Suite | Passing |\n'
+  printf '|-------|---------|\n'
+  printf '| All Smalltalk-on-SX tests | **%s / %s** |\n' "$ALL_PASS" "$ALL_TOTAL"
+  printf '| Classic-corpus tests (`tests/programs.sx`) | **%s** |\n\n' "$PROG_PASS"
+
+  printf '## Classic-corpus programs (`lib/smalltalk/tests/programs/`)\n\n'
+  printf '| Program | Status |\n'
+  printf '|---------|--------|\n'
+  for prog in "${PROGRAMS[@]}"; do
+    printf '| `%s.st` | present |\n' "$prog"
+  done
+  printf '\n'
+
+  printf '## Per-file test counts\n\n'
+  printf '```\n'
+  echo "$RUNNER_OUT" | grep -E '^(OK|X) lib/smalltalk/tests/' | sort
+  printf '```\n\n'
+
+  printf '## Notes\n\n'
+  printf -- '- The spec interpreter is correct but slow (call/cc + dict-based ivars per send).\n'
+  printf -- '- Larger Life multi-step verification, the 8-queens canonical case, and the glider-gun pattern are deferred to the JIT path.\n'
+  printf -- '- Generated by `bash lib/smalltalk/conformance.sh`. Both files are committed; the runner overwrites them on each run.\n'
+} > "$OUT_MD"
+
+echo "Scoreboard updated:"
+echo "  $OUT_JSON"
+echo "  $OUT_MD"
+echo "Programs: $NUM_PROGRAMS  Corpus tests: $PROG_PASS  All: $ALL_PASS/$ALL_TOTAL"
+
+exit $RC
diff --git a/lib/smalltalk/scoreboard.json b/lib/smalltalk/scoreboard.json
new file mode 100644
index 00000000..d9c5ff43
--- /dev/null
+++ b/lib/smalltalk/scoreboard.json
@@ -0,0 +1,15 @@
+{
+  "date": "2026-04-25T07:53:18Z",
+  "programs": [
+    "eight-queens.st",
+    "fibonacci.st",
+    "life.st",
+    "mandelbrot.st",
+    "quicksort.st"
+  ],
+  "program_count": 5,
+  "program_tests_passed": 39,
+  "all_tests_passed": 403,
+  "all_tests_total": 403,
+  "exit_code": 0
+}
diff --git a/lib/smalltalk/scoreboard.md b/lib/smalltalk/scoreboard.md
new file mode 100644
index 00000000..5d4c6230
--- /dev/null
+++ b/lib/smalltalk/scoreboard.md
@@ -0,0 +1,44 @@
+# Smalltalk-on-SX Scoreboard
+
+_Last run: 2026-04-25T07:53:18Z_
+
+## Totals
+
+| Suite | Passing |
+|-------|---------|
+| All Smalltalk-on-SX tests | **403 / 403** |
+| Classic-corpus tests (`tests/programs.sx`) | **39** |
+
+## Classic-corpus programs (`lib/smalltalk/tests/programs/`)
+
+| Program | Status |
+|---------|--------|
+| `eight-queens.st` | present |
+| `fibonacci.st` | present |
+| `life.st` | present |
+| `mandelbrot.st` | present |
+| `quicksort.st` | present |
+
+## Per-file test counts
+
+```
+OK lib/smalltalk/tests/blocks.sx            19 passed
+OK lib/smalltalk/tests/cannot_return.sx     5 passed
+OK lib/smalltalk/tests/conditional.sx       25 passed
+OK lib/smalltalk/tests/dnu.sx               15 passed
+OK lib/smalltalk/tests/eval.sx              68 passed
+OK lib/smalltalk/tests/nlr.sx               14 passed
+OK lib/smalltalk/tests/parse_chunks.sx      21 passed
+OK lib/smalltalk/tests/parse.sx             47 passed
+OK lib/smalltalk/tests/programs.sx          39 passed
+OK lib/smalltalk/tests/runtime.sx           64 passed
+OK lib/smalltalk/tests/super.sx             9 passed
+OK lib/smalltalk/tests/tokenize.sx          63 passed
+OK lib/smalltalk/tests/while.sx             14 passed
+```
+
+## Notes
+
+- The spec interpreter is correct but slow (call/cc + dict-based ivars per send).
+- Larger Life multi-step verification, the 8-queens canonical case, and the glider-gun pattern are deferred to the JIT path.
+- Generated by `bash lib/smalltalk/conformance.sh`. Both files are committed; the runner overwrites them on each run.
diff --git a/plans/smalltalk-on-sx.md b/plans/smalltalk-on-sx.md
index 5bbb2648..1408abab 100644
--- a/plans/smalltalk-on-sx.md
+++ b/plans/smalltalk-on-sx.md
@@ -76,7 +76,7 @@ Core mapping:
   - [x] `mandelbrot.st` — escape-time iteration of `z := z² + c` in `lib/smalltalk/tests/programs/mandelbrot.st`. Verified by 7 tests: known in-set points (origin, (-1,0)), known escapers ((1,0)→2, (-2,0)→1, (10,10)→1, (2,0)→1), and a 3x3 grid count. Caught a real bug along the way: literal `#(...)` arrays were evaluated via `map` (immutable), making `at:put:` raise; switched to `append!` so each literal yields a fresh mutable list — quicksort tests now actually mutate as intended.
   - [x] `life.st` (Conway's Life). `lib/smalltalk/tests/programs/life.st` carries the canonical rules with edge handling. Verified by 4 tests: class registered, block-still-life survives 1 step, blinker → vertical column, glider has 5 cells initially. Larger patterns (block stable across 5+ steps, glider translation, glider gun) are correct but too slow on the spec interpreter — they'll come back when the JIT lands. Also added Pharo-style dynamic array literal `{e1. e2. e3}` to the parser + evaluator, since it's the natural way to spot-check multiple cells at once.
   - [x] `fibonacci.st` (recursive + Array-memoised) — `lib/smalltalk/tests/programs/fibonacci.st`. Loaded from chunk-format source by new `smalltalk-load` helper; verified by 13 tests in `lib/smalltalk/tests/programs.sx` (recursive `fib:`, memoised `memoFib:` up to 30, instance independence, class-table integrity). Source is currently duplicated as a string in the SX test file because there's no SX file-read primitive; conformance.sh will dedupe by piping the .st file directly.
-- [ ] `lib/smalltalk/conformance.sh` + runner, `scoreboard.json` + `scoreboard.md`
+- [x] `lib/smalltalk/conformance.sh` + runner, `scoreboard.json` + `scoreboard.md`. The runner runs `bash lib/smalltalk/test.sh -v` once, parses per-file counts, and emits both files. JSON has date / program names / corpus-test count / all-test pass/total / exit code. Markdown has a totals table, the program list, the verbatim per-file test counts block, and notes about JIT-deferred work. Both are checked into the tree as the latest baseline; the runner overwrites them.
 
 ### Phase 4 — reflection + MOP
 - [ ] `Object>>class`, `class>>name`, `class>>superclass`, `class>>methodDict`, `class>>selectors`
@@ -108,6 +108,7 @@ Core mapping:
 
 _Newest first. Agent appends on every commit._
 
+- 2026-04-25: conformance.sh + scoreboard.{json,md} (`lib/smalltalk/conformance.sh`, `lib/smalltalk/scoreboard.json`, `lib/smalltalk/scoreboard.md`). Single-pass runner over `test.sh -v`; baseline at 5 programs / 39 corpus tests / 403 total. **Phase 3 complete.**
 - 2026-04-25: classic-corpus #5 Life (`tests/programs/life.st`, 4 tests). Spec-interpreter Conway's Life with edge handling. Block + blinker + glider initial setup verified; larger step counts pending JIT (each spec-interpreter step is ~5-8s on a 5x5 grid). Added `{e1. e2. e3}` dynamic array literal to parser + evaluator. 403/403 total.
 - 2026-04-25: classic-corpus #4 mandelbrot (`tests/programs/mandelbrot.st`, 7 tests). Escape-time iterator + grid counter. Discovered + fixed an immutable-list bug in `lit-array` eval — `map` produced an immutable list so `at:put:` raised; rebuilt via `append!`. Quicksort tests had been silently dropping ~7 cases due to that bug; now actually mutate. 399/399 total.
 - 2026-04-25: classic-corpus #3 quicksort (`tests/programs/quicksort.st`, 9 tests). Lomuto partition; verified across duplicates, already-sorted/reverse-sorted, empty, single, negatives, all-equal, plus in-place mutation. 385/385 total.