Files
rose-ash/lib/artdag/conformance.sh
giles a2f4fb5e89
Some checks failed
Test, Build, and Deploy / test-build-deploy (push) Failing after 50s
artdag: Phase 4 Execute — content-addressed memo + incremental recompute + 15 tests
execute.sx folds a plan, runs each node via an injected runner (perform in
prod, op-table in tests), and memoizes results in a lib/persist kv backend
keyed by content-id. Incremental recompute falls out of content addressing:
a leaf change reassigns ids across its dirty closure, so re-running hits the
unchanged nodes and recomputes only the closure (cold 5 -> rerun 0 -> change 3).
Cross-dag subgraph sharing verified. execute 15/15, total 69/69.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-07 12:00:50 +00:00

125 lines
3.4 KiB
Bash
Executable File

#!/usr/bin/env bash
# lib/artdag/conformance.sh — run artdag test suites, emit scoreboard.json + scoreboard.md.
set -uo pipefail
cd "$(git rev-parse --show-toplevel)"
SX_SERVER="${SX_SERVER:-/root/rose-ash/hosts/ocaml/_build/default/bin/sx_server.exe}"
if [ ! -x "$SX_SERVER" ]; then
SX_SERVER="hosts/ocaml/_build/default/bin/sx_server.exe"
fi
if [ ! -x "$SX_SERVER" ]; then
echo "ERROR: sx_server.exe not found." >&2
exit 1
fi
SUITES=(dag analyze plan execute)
OUT_JSON="lib/artdag/scoreboard.json"
OUT_MD="lib/artdag/scoreboard.md"
run_suite() {
local suite=$1
local file="lib/artdag/tests/${suite}.sx"
local TMP
TMP=$(mktemp)
cat > "$TMP" << EPOCHS
(epoch 1)
(load "spec/stdlib.sx")
(load "lib/r7rs.sx")
(load "lib/datalog/tokenizer.sx")
(load "lib/datalog/parser.sx")
(load "lib/datalog/unify.sx")
(load "lib/datalog/db.sx")
(load "lib/datalog/builtins.sx")
(load "lib/datalog/aggregates.sx")
(load "lib/datalog/strata.sx")
(load "lib/datalog/eval.sx")
(load "lib/datalog/api.sx")
(load "lib/persist/event.sx")
(load "lib/persist/backend.sx")
(load "lib/persist/log.sx")
(load "lib/persist/kv.sx")
(load "lib/persist/api.sx")
(load "lib/artdag/dag.sx")
(load "lib/artdag/analyze.sx")
(load "lib/artdag/plan.sx")
(load "lib/artdag/execute.sx")
(epoch 2)
(eval "(define artdag-test-pass 0)")
(eval "(define artdag-test-fail 0)")
(eval "(define artdag-test (fn (name got expected) (if (= got expected) (set! artdag-test-pass (+ artdag-test-pass 1)) (set! artdag-test-fail (+ artdag-test-fail 1)))))")
(epoch 3)
(load "${file}")
(epoch 4)
(eval "(list artdag-test-pass artdag-test-fail)")
EPOCHS
local OUTPUT
OUTPUT=$(timeout 300 "$SX_SERVER" < "$TMP" 2>/dev/null)
rm -f "$TMP"
local LINE
LINE=$(echo "$OUTPUT" | awk '/^\(ok-len 4 / {getline; print; exit}')
if [ -z "$LINE" ]; then
LINE=$(echo "$OUTPUT" | grep -E '^\(ok 4 \([0-9]+ [0-9]+\)\)' | tail -1 \
| sed -E 's/^\(ok 4 //; s/\)$//')
fi
local P F
P=$(echo "$LINE" | sed -E 's/^\(([0-9]+) ([0-9]+)\).*/\1/')
F=$(echo "$LINE" | sed -E 's/^\(([0-9]+) ([0-9]+)\).*/\2/')
P=${P:-0}
F=${F:-0}
echo "${P} ${F}"
}
declare -A SUITE_PASS
declare -A SUITE_FAIL
TOTAL_PASS=0
TOTAL_FAIL=0
echo "Running artdag conformance suite..." >&2
for s in "${SUITES[@]}"; do
read -r p f < <(run_suite "$s")
SUITE_PASS[$s]=$p
SUITE_FAIL[$s]=$f
TOTAL_PASS=$((TOTAL_PASS + p))
TOTAL_FAIL=$((TOTAL_FAIL + f))
printf " %-12s %d/%d\n" "$s" "$p" "$((p+f))" >&2
done
{
printf '{\n'
printf ' "suites": {\n'
first=1
for s in "${SUITES[@]}"; do
if [ $first -eq 0 ]; then printf ',\n'; fi
printf ' "%s": {"pass": %d, "fail": %d}' "$s" "${SUITE_PASS[$s]}" "${SUITE_FAIL[$s]}"
first=0
done
printf '\n },\n'
printf ' "total_pass": %d,\n' "$TOTAL_PASS"
printf ' "total_fail": %d,\n' "$TOTAL_FAIL"
printf ' "total": %d\n' "$((TOTAL_PASS + TOTAL_FAIL))"
printf '}\n'
} > "$OUT_JSON"
{
printf '# artdag Conformance Scoreboard\n\n'
printf '_Generated by `lib/artdag/conformance.sh`_\n\n'
printf '| Suite | Pass | Fail | Total |\n'
printf '|-------|-----:|-----:|------:|\n'
for s in "${SUITES[@]}"; do
p=${SUITE_PASS[$s]}
f=${SUITE_FAIL[$s]}
printf '| %s | %d | %d | %d |\n' "$s" "$p" "$f" "$((p+f))"
done
printf '| **Total** | **%d** | **%d** | **%d** |\n' "$TOTAL_PASS" "$TOTAL_FAIL" "$((TOTAL_PASS + TOTAL_FAIL))"
} > "$OUT_MD"
echo "Wrote $OUT_JSON and $OUT_MD" >&2
echo "Total: $TOTAL_PASS pass, $TOTAL_FAIL fail" >&2
[ "$TOTAL_FAIL" -eq 0 ]