#!/usr/bin/env bash
# M3 JSON-parity gate. Pure C harness (NOT elb/elc): links the real el_runtime.c
# native engram builtins + engram_store.c and drives ENGRAM_STORE on vs off.
# Writes ONLY under a throwaway /tmp dir with a throwaway HOME + ENGRAM_DATA_DIR.
set -u
HERE="$(cd "$(dirname "$0")" && pwd)"
RT="$HERE/../../lang/runtime/el_runtime.c"
ST="$HERE/../../lang/runtime/engram_store.c"
INC="$HERE/../../lang/runtime"
WORK="$(mktemp -d /tmp/engram-m3-XXXXXX)"
DATA="$WORK/data"; mkdir -p "$DATA"
BIN="$WORK/m3"
export HOME="$WORK/home"; mkdir -p "$HOME"          # never touch real ~/.neuron
export ENGRAM_DATA_DIR="$DATA"
export ENGRAM_WAL_SYNC=always
unset ENGRAM_STORE
fail=0

echo "== compiling harness (gcc: el_runtime.c + engram_store.c + test_m3_parity.c) =="
gcc -O1 -std=c11 -I "$INC" "$HERE/test_m3_parity.c" "$RT" "$ST" -lcurl -o "$BIN" 2>"$WORK/cc.log"
if [ $? -ne 0 ]; then echo "COMPILE FAILED:"; cat "$WORK/cc.log"; rm -rf "$WORK"; exit 1; fi
grep -i warning "$WORK/cc.log" | grep -iE 'engram_store|eg_store|eg_load|scan_nodes|scan_edges' && echo "(warnings in M3 code above)" || true

echo
echo "== 0) default-OFF: flag unset leaves the store untouched =="
( unset ENGRAM_STORE; "$BIN" offcheck "$DATA" )
[ $? -ne 0 ] && { echo "FAIL: offcheck"; fail=1; }
[ -e "$DATA/neuron.egm" ] && { echo "FAIL: neuron.egm created while flag OFF"; fail=1; } \
                          || echo "  ok: no neuron.egm created with flag OFF"

echo
echo "== 1) seed (ENGRAM_STORE unset): build graph, save snapshot.json, activate =="
( unset ENGRAM_STORE; "$BIN" seed "$DATA" ) || { echo "FAIL: seed"; fail=1; }

echo
echo "== 2) on (ENGRAM_STORE=1): import snapshot.json ONCE -> neuron.egm, resident-load, activate =="
ENGRAM_STORE=1 "$BIN" on "$DATA" || { echo "FAIL: on"; fail=1; }
[ -e "$DATA/neuron.egm" ] && echo "  ok: neuron.egm created by import" || { echo "FAIL: neuron.egm missing"; fail=1; }

echo
echo "== 3) reboot (ENGRAM_STORE=1, snapshot.json DELETED): must load from neuron.egm, never JSON =="
rm -f "$DATA/snapshot.json"
ENGRAM_STORE=1 "$BIN" reboot "$DATA" || { echo "FAIL: reboot"; fail=1; }

echo
echo "== 4) parity comparison (modulo ordering) =="
python3 - "$DATA" <<'PY'
import json, sys, os
d = sys.argv[1]
def load(name):
    with open(os.path.join(d, name)) as f: return json.load(f)
def norm_graph(g):
    nodes = sorted(g.get("nodes", []), key=lambda n: n.get("id",""))
    edges = sorted(g.get("edges", []), key=lambda e: e.get("id",""))
    layers= sorted(g.get("layers", []), key=lambda l: l.get("layer_id",0))
    return {"nodes":nodes, "edges":edges, "layers":layers}
def act_ids(a):
    # list of (node id, promoted); robust set + ordered list
    seq = [(e.get("node",{}).get("id",""), int(e.get("promoted",0))) for e in a]
    return seq

rc = 0
snap  = norm_graph(load("snapshot.json") if os.path.exists(os.path.join(d,"snapshot.json")) else load("off_graph.json"))
off   = norm_graph(load("off_graph.json"))
on    = norm_graph(load("on_graph.json"))
rebt  = norm_graph(load("reboot_graph.json"))

def cmp(label, a, b):
    global rc
    if a == b:
        print(f"  PASS: {label}  (nodes={len(a['nodes'])} edges={len(a['edges'])} layers={len(a['layers'])})")
    else:
        rc = 1
        print(f"  FAIL: {label}")
        for k in ("nodes","edges","layers"):
            if a[k] != b[k]:
                print(f"    {k}: {len(a[k])} vs {len(b[k])}")
                for x,y in zip(a[k], b[k]):
                    if x != y:
                        print(f"    first diff:\n      A={json.dumps(x)[:300]}\n      B={json.dumps(y)[:300]}")
                        break

cmp("graph: ENGRAM_STORE=1 (export) == ENGRAM_STORE=0 (JSON path)", on, off)
cmp("round-trip: snapshot.json seed == store export (on_graph)", on, off)  # off_graph==snapshot save
cmp("reboot from neuron.egm (no JSON) == on-path store", rebt, on)

offa = act_ids(load("off_act.json"))
ona  = act_ids(load("on_act.json"))
if set(offa) == set(ona):
    print(f"  PASS: activation result set identical  (off={len(offa)} on={len(ona)} entries)")
    if offa == ona:
        print("        (and identical ordering/promotion sequence)")
    else:
        print("        (same set; ordering differs only where scores tie — reporting honestly)")
else:
    rc = 1
    print("  FAIL: activation result set differs")
    print(f"    off-only: {set(offa)-set(ona)}")
    print(f"    on-only:  {set(ona)-set(offa)}")

sys.exit(rc)
PY
[ $? -ne 0 ] && fail=1

echo
echo "== 5) ASan+UBSan build, exercise M3 scan/boot/hooks (leaks off — harness intentionally leaks el_strdup) =="
SANBIN="$WORK/m3.san"
gcc -O1 -g -std=c11 -fsanitize=address,undefined -fno-sanitize-recover=undefined \
    -I "$INC" "$HERE/test_m3_parity.c" "$RT" "$ST" -lcurl -o "$SANBIN" 2>"$WORK/san_cc.log"
if [ $? -ne 0 ]; then echo "  SAN COMPILE FAILED:"; tail -20 "$WORK/san_cc.log"; fail=1; else
  export ASAN_OPTIONS=detect_leaks=0
  DATA2="$WORK/data2"; mkdir -p "$DATA2"
  ( unset ENGRAM_STORE; "$SANBIN" seed "$DATA2" ) >/dev/null 2>"$WORK/san_run.log" && \
  ENGRAM_STORE=1 "$SANBIN" on "$DATA2" >/dev/null 2>>"$WORK/san_run.log" && \
  { rm -f "$DATA2/snapshot.json"; ENGRAM_STORE=1 "$SANBIN" reboot "$DATA2" >/dev/null 2>>"$WORK/san_run.log"; }
  if grep -qiE 'runtime error|AddressSanitizer|UndefinedBehavior|ERROR: ' "$WORK/san_run.log"; then
    echo "  FAIL: sanitizer findings:"; grep -iE 'runtime error|Sanitizer|ERROR' "$WORK/san_run.log" | head; fail=1
  else
    echo "  ok: ASan+UBSan clean across seed/on/reboot (scan, boot, resident-load, mutation hooks)"
  fi
fi

echo
if [ "$fail" -eq 0 ]; then echo "================  M3 PARITY GATE: PASS  ================"; else echo "================  M3 PARITY GATE: FAIL  ================"; fi
rm -rf "$WORK"
exit $fail