#!/usr/bin/env bash
# Reproduction rig for the load-sensitivity flake in symbolic summary
# recomputation (fold optimization loop iteration 5; see
# docs/research/optimization-loop-2026-07-30.md).
#
# Observed once (2026-07-31): the characterization test
# 'repeated nested summary computation stays stable across a reused
# scratch context' produced an empty return_post ('' vs 'arg0') in a
# 7/10-run burst while background fold scans saturated the machine,
# then passed 16/16 on a quiet machine with byte-identical production
# code. Three bounded rig attempts (2026-07-31) failed to reproduce:
#   1. 8 subshell busy-loops + 10 filtered test runs        -> 10/10 PASS
#   2. 8 `yes` workers (verified via uptime) + 10 full runs -> 10/10 PASS
#   3. concurrent real fold sql-injection+uninit-read scan
#      (-j 4, Z3 contexts churning) + 10 full runs          -> 10/10 PASS
# Prime suspect remains isValidPredicate()'s 100ms Z3 solver timeout
# (summary_encoder.cpp): under CPU starvation check() returns unknown
# and predicate-record decisions flip. The flake window may also
# involve memory pressure or specific solver states not covered by the
# small fixture. Re-run this rig after scanner changes that touch the
# summary path; escalate to deterministic predicate decisions if it
# ever reproduces.
#
# Usage: tests/benchmarks/run_summary_flake_rig.sh [build-dir]
set -euo pipefail
BUILD_DIR="${1:-build/release}"
TEST_BIN="$BUILD_DIR/tests/unit/test_symbolic_summary"
cd "$(dirname "$0")/../.."

[[ -x "$TEST_BIN" ]] || {
  echo "test binary missing: $TEST_BIN" >&2
  exit 2
}

for i in 1 2 3 4 5 6 7 8; do yes >/dev/null & done
trap 'kill $(jobs -p) 2>/dev/null || true' EXIT
sleep 2
echo "load during run: $(uptime)"

PASS=0
FAIL=0
for i in $(seq 1 10); do
  if "$TEST_BIN" >"/tmp/summary-flake-rig-$i.log" 2>&1; then
    PASS=$((PASS + 1))
  else
    FAIL=$((FAIL + 1))
    echo "FAILED run $i: /tmp/summary-flake-rig-$i.log" >&2
  fi
done
echo "summary-flake rig: PASS=$PASS FAIL=$FAIL"
[[ "$FAIL" -eq 0 ]]