#!/bin/bash
# test-differential.sh — W14/F8: cross-host differential battery.
#
# Evaluates every expression in spec/tests/differential-probes.txt on:
#   A) the native server (sx_server.exe, epoch protocol) — its printer
#   B) the SHIPPED browser kernel (eval_wasm_probes.js, guest sx-serialize)
# and diffs the outputs. The review's original 130-probe corpus was
# ephemeral (F-8); this is the committed replacement.
#
# KNOWN_DIVERGENT is the ledger of confirmed, still-open divergences —
# keyed by the probe EXPRESSION. Red on a NEW divergence (host drift) and
# red on a HEALED one (fix landed: delete the entry, locking in parity).
#
# Method note (finding refinement, 2026-07-04): comparing raw K.eval
# JS-boundary values shows float-display divergences (0.3 vs
# 0.30000000000000004) that DISAPPEAR under guest-level (sx-serialize …) —
# the F-1 float-display class is a JS-boundary artifact, not a kernel
# serialization divergence. This battery compares guest serialization.
set -uo pipefail
cd "$(dirname "$0")/.."

SERVER=hosts/ocaml/_build/default/bin/sx_server.exe
WASM=shared/static/wasm/sx_browser.bc.wasm.js
PROBES=spec/tests/differential-probes.txt
[[ -x "$SERVER" ]] || { echo "SKIP: $SERVER not built" >&2; exit 2; }
[[ -f "$WASM" ]] || { echo "SKIP: $WASM missing" >&2; exit 2; }

# --- KNOWN_DIVERGENT ledger (verified live 2026-07-04) -------------------
# F-3/K53: bare sx_server's `apply` does NOT spread its argument list —
# (apply + (list 1 2 3)) errors "Expected number, got list"; (apply str l)
# returns the serialized list as one string. The WASM kernel spreads
# correctly. The test runner masks this with its own apply (F-7 class).
declare -A KNOWN_DIVERGENT
KNOWN_DIVERGENT['(apply + (list 1 2 3))']="F-3: native apply does not spread"
KNOWN_DIVERGENT['(apply max (list 1 5 2))']="F-3: native apply does not spread"
KNOWN_DIVERGENT['(apply str (list "a" "b"))']="F-3: native apply does not spread"

native=$(mktemp); wasm=$(mktemp)

python3 - "$SERVER" "$PROBES" > "$native" <<'PY'
import json, subprocess, sys
server, probefile = sys.argv[1], sys.argv[2]
probes = [l.strip() for l in open(probefile) if l.strip() and not l.startswith('#')]
inp = []
for i, p in enumerate(probes):
    inp.append(f"(epoch {i+1})")
    inp.append(f"(eval {json.dumps(p)})")
out = subprocess.run(["timeout", "120", server], input="\n".join(inp) + "\n",
                     capture_output=True, text=True).stdout
res, cur = {}, None
for l in out.splitlines():
    if l.startswith("(ok-len "):
        cur = int(l.split()[1]); res[cur] = None
    elif l.startswith("(error "):
        idx = int(l.split()[1]); res[idx] = "ERROR"; cur = None
    elif cur is not None and res.get(cur) is None:
        res[cur] = l; cur = None
for i, p in enumerate(probes):
    print(f"PROBE {i+1} {res.get(i+1, '<none>')}")
PY

timeout 300 node hosts/ocaml/browser/eval_wasm_probes.js "$PROBES" > "$wasm" 2>/dev/null

pass=0; fail=0; i=0
while IFS= read -r expr; do
  [[ -z "$expr" || "$expr" == \#* ]] && continue
  i=$((i+1))
  a=$(sed -n "s/^PROBE $i //p" "$native")
  b=$(sed -n "s/^PROBE $i //p" "$wasm")
  known="${KNOWN_DIVERGENT[$expr]:-}"
  if [[ "$a" == "$b" ]]; then
    if [[ -n "$known" ]]; then
      echo "RED:  $expr — KNOWN_DIVERGENT now AGREES ($known); delete from ledger"
      fail=$((fail+1))
    else
      pass=$((pass+1))
    fi
  else
    if [[ -n "$known" ]]; then
      echo "KNOWN-DIVERGENT: $expr ($known)"
      pass=$((pass+1))
    else
      echo "RED:  $expr"
      echo "        native: $a"
      echo "        wasm:   $b"
      fail=$((fail+1))
    fi
  fi
done < <(grep -v '^\s*#' "$PROBES" | grep -v '^\s*$')

rm -f "$native" "$wasm"
echo
echo "differential: $i probes, $pass in agreement/ledgered, $fail red"
[[ $fail -eq 0 ]]