#!/usr/bin/env bash
# ────────────────────────────────────────────────────────────────────────────
# lean-guard — HARD-CAPPED Lean compiler wrapper.
#
# Successor to lean-safe after the 2026-07-02 OOM incident: a single `lean`
# elaboration (tactic-search blowup: simp[*]/scalar_tac over a ~60-hypothesis
# context with 2^256-scale literals) grew to 12.2GB RSS and was killed by the
# GLOBAL kernel OOM killer, taking the driving session down with it.
# lean-safe's guards (timeout + affinity + PREFLIGHT headroom) cannot stop
# that: the process passes preflight, then balloons inside its timeout.
#
# NEW GUARDS (in addition to all lean-safe guards):
#   A. lean -M <MB>                  — Lean's internal cap: elaboration aborts
#                                      with a clean "maximum memory exceeded"
#                                      error. First line of defense; graceful.
#   B. systemd-run --user --scope
#        -p MemoryMax / MemorySwapMax — kernel cgroup cap around the process:
#                                      if Lean's own accounting misses (C-level
#                                      allocations), the cgroup kills ONLY this
#                                      lean, never the session, never the box.
#   C. flock on /tmp/lean-guard.lock — machine-wide single-flight: at most ONE
#                                      lean compile at a time, regardless of
#                                      how many agents/scripts are active.
#
# Env knobs (defaults for this 14GB / 8-core ThinkPad):
#   LEAN_TIMEOUT      per-file wall clock seconds        (default 400)
#   LEAN_MEM_MB       lean -M internal cap, MB           (default 4096)
#   LEAN_CGROUP_MB    cgroup MemoryMax, MB               (default LEAN_MEM_MB+1024)
#   LEAN_MAX_CORES    taskset core range                 (default 0-3)
#   LEAN_MIN_FREE_MB  preflight available-RAM floor      (default 3072)
#   LEAN_LOCK_WAIT    max seconds to wait for the lock   (default 7200)
#
# Usage:  lean-guard <file.lean> [extra lean args...]
# The .olean output path is always computed as ${file%.lean}.olean.
# Requires: lean on PATH (caller sources the toolchain env; typically run
# inside `lake env` so LEAN_PATH is set — this wrapper does NOT clobber env).
# ────────────────────────────────────────────────────────────────────────────
set -uo pipefail

# No core dumps: hitting the memory cap makes lean (and uutils `timeout`) abort;
# those aborts are EXPECTED and their core dumps only trigger Ubuntu apport
# popups and fill /var/crash. ulimit applies to this shell and every child.
ulimit -c 0 2>/dev/null || true

TIMEOUT_SEC=${LEAN_TIMEOUT:-400}
MEM_MB=${LEAN_MEM_MB:-4096}
CGROUP_MB=${LEAN_CGROUP_MB:-$((MEM_MB + 1024))}
CORES=${LEAN_MAX_CORES:-0-3}
MIN_FREE_MB=${LEAN_MIN_FREE_MB:-3072}
LOCK_WAIT=${LEAN_LOCK_WAIT:-7200}
LOCK_FILE=/tmp/lean-guard.lock
LOG_FILE="${HOME}/.lean-guard.log"

if ! command -v lean &>/dev/null; then
    echo "FATAL: lean not on PATH — source ~/aeneas-toolchain/env.sh (and run inside lake env)"
    exit 1
fi
if [ $# -eq 0 ]; then
    echo "Usage: lean-guard <file.lean> [lean args...]"
    exit 1
fi

LEAN_FILE="$1"; shift || true

# ── Guard 1: source integrity (anti olean-clobber) ──────────────────────────
if [ ! -f "$LEAN_FILE" ]; then
    echo "MISSING: $LEAN_FILE"; exit 1
fi
if ! grep -qE '^[[:space:]]*(/-|import |namespace |theorem |def |open |set_option |--)' "$LEAN_FILE" 2>/dev/null; then
    echo "FATAL: $LEAN_FILE is not Lean source (binary/olean data?)."
    echo "  Restore: git checkout HEAD -- $LEAN_FILE"
    exit 1
fi

# ── Guard 2: output path ─────────────────────────────────────────────────────
case "$LEAN_FILE" in
  *.lean) ;;
  *) echo "FATAL: input lacks .lean extension"; exit 1 ;;
esac
OLEAN_FILE="${LEAN_FILE%.lean}.olean"
[ "$OLEAN_FILE" = "$LEAN_FILE" ] && { echo "FATAL: output would clobber source"; exit 1; }

# ── Guard C: machine-wide single-flight ─────────────────────────────────────
exec 9>"$LOCK_FILE"
if ! flock -w "$LOCK_WAIT" 9; then
    echo "FATAL: could not acquire lean-guard lock within ${LOCK_WAIT}s (another compile stuck?)"
    exit 1
fi

# ── Guard 3: preflight headroom (after lock: serialized measurement) ────────
AVAIL_MB=$(free -m | awk '/Mem:/{print $7}')
if [ "$AVAIL_MB" -lt "$MIN_FREE_MB" ]; then
    echo "FATAL: only ${AVAIL_MB}MB available (< ${MIN_FREE_MB}MB floor) — refusing to compile"
    exit 1
fi


# ── Guard 3b: global-headroom clamp (2026-07-03 swap-pressure incident) ─────
# A cap is a PROMISE of memory to lean; never promise more than the machine
# can afford right now. Requested caps that exceed (available − floor) are
# clamped, so raising LEAN_MEM_MB can no longer starve the rest of the system
# into swap even when lean itself stays within its cap. Clamp, don't fail:
# most compiles peak far below their cap (measure before raising — the
# incident's 9G scopes served a file whose true peak was 753MB).
REQ_MEM_MB=$MEM_MB
WAS_CLAMPED=0
MAX_AFFORD_MB=$(( AVAIL_MB - MIN_FREE_MB ))
if [ "$MEM_MB" -gt "$MAX_AFFORD_MB" ]; then
    echo "lean-guard: clamping -M ${MEM_MB} -> ${MAX_AFFORD_MB}MB (avail=${AVAIL_MB}MB, floor=${MIN_FREE_MB}MB)"
    MEM_MB=$MAX_AFFORD_MB
    CGROUP_MB=$(( MEM_MB + 1024 ))
    WAS_CLAMPED=1
fi
if [ "$MEM_MB" -lt 1024 ]; then
    echo "FATAL: headroom clamp would leave lean < 1024MB — machine too loaded to compile safely"
    exit 1
fi

echo "[$(date -u +%F' '%T)] $LEAN_FILE (t=${TIMEOUT_SEC}s M=${MEM_MB}MB cg=${CGROUP_MB}MB cores=$CORES avail=${AVAIL_MB}MB)" >> "$LOG_FILE"

# ── Compile under both caps ──────────────────────────────────────────────────
run_leancmd() {
    taskset -c "$CORES" \
      timeout --signal=TERM --kill-after=15 "$TIMEOUT_SEC" \
      lean -M "$MEM_MB" -o "$OLEAN_FILE" "$LEAN_FILE" "$@"
}
do_compile() {
    if systemd-run --user --scope -p MemoryMax=10M --quiet -- /bin/true 2>/dev/null; then
        # --scope runs the command as a child of THIS shell (env inherited),
        # merely placing it in a fresh cgroup with the hard caps below.
        systemd-run --user --scope --quiet \
            -p MemoryMax="${CGROUP_MB}M" -p MemorySwapMax=256M \
            -- taskset -c "$CORES" \
               timeout --signal=TERM --kill-after=15 "$TIMEOUT_SEC" \
               lean -M "$MEM_MB" -o "$OLEAN_FILE" "$LEAN_FILE" "$@"
    else
        echo "  (systemd-run unavailable — falling back to lean -M only)" >> "$LOG_FILE"
        run_leancmd "$@"
    fi
}
do_compile "$@"
EXIT_CODE=$?

# ── Guard 3a: lazy wait-and-retry after a clamped memory abort (pass 3) ─────
# The clamp above protects the host, but under ambient memory pressure it
# can cut a KNOWN-NEEDED cap (ReduceSpec peaks ~6.5G) and guarantee an
# interpreter abort that reads like a proof regression. Lazy semantics keep
# light files free: only when a CLAMPED run dies on memory (134 abort /
# 137 cgroup kill) and LEAN_MEM_WAIT_SEC>0, wait — still under the
# single-flight lock — until the ORIGINAL request is affordable, then retry
# once at full cap. Default 0: behavior unchanged.
MEM_WAIT_SEC=${LEAN_MEM_WAIT_SEC:-0}
if [ "$WAS_CLAMPED" -eq 1 ] && [ "$MEM_WAIT_SEC" -gt 0 ]; then
    WAITED=0
    # Retry ladder: whenever headroom improves MATERIALLY (>= +1536MB over
    # the cap that just died, or reaches the full request), retry at the
    # new clamp. The full request may never be affordable on a loaded host
    # even though the true peak is — climbing the ladder finds the passing
    # clamp without knowing the peak. Monotone caps + deadline => bounded.
    while { [ "$EXIT_CODE" -eq 134 ] || [ "$EXIT_CODE" -eq 137 ]; } \
          && [ "$WAITED" -lt "$MEM_WAIT_SEC" ] && [ "$MEM_MB" -lt "$REQ_MEM_MB" ]; do
        sleep 20; WAITED=$(( WAITED + 20 ))
        AVAIL_MB=$(free -m | awk '/Mem:/{print $7}')
        NEW_AFFORD=$(( AVAIL_MB - MIN_FREE_MB ))
        if [ "$NEW_AFFORD" -ge "$REQ_MEM_MB" ] || [ "$NEW_AFFORD" -ge $(( MEM_MB + 1536 )) ]; then
            MEM_MB=$(( NEW_AFFORD < REQ_MEM_MB ? NEW_AFFORD : REQ_MEM_MB ))
            CGROUP_MB=$(( MEM_MB + 1024 ))
            echo "lean-guard: clamped run died (rc=$EXIT_CODE); retrying at -M ${MEM_MB}MB after ${WAITED}s (avail=${AVAIL_MB}MB, request=${REQ_MEM_MB}MB)"
            echo "[$(date -u +%F' '%T)] RETRY $LEAN_FILE (M=${MEM_MB}MB cg=${CGROUP_MB}MB avail=${AVAIL_MB}MB after ${WAITED}s)" >> "$LOG_FILE"
            do_compile "$@"
            EXIT_CODE=$?
        fi
    done
    if [ "$EXIT_CODE" -eq 134 ] || [ "$EXIT_CODE" -eq 137 ]; then
        echo "lean-guard: memory-death persists after ${WAITED}s of ladder retries (last -M ${MEM_MB}MB, request ${REQ_MEM_MB}MB) — keeping the failure"
    fi
fi

case $EXIT_CODE in
  0)   echo "  OK" >> "$LOG_FILE" ;;
  124) echo "  TIMEOUT ${TIMEOUT_SEC}s" >> "$LOG_FILE"
       echo "TIMEOUT: $LEAN_FILE exceeded ${TIMEOUT_SEC}s" ;;
  137) echo "  KILLED (cgroup MemoryMax ${CGROUP_MB}MB hit)" >> "$LOG_FILE"
       echo "KILLED: $LEAN_FILE hit the ${CGROUP_MB}MB cgroup cap (contained — machine unharmed)" ;;
  *)   echo "  FAILED exit $EXIT_CODE (lean error, possibly '-M ${MEM_MB}MB exceeded')" >> "$LOG_FILE" ;;
esac
# stale partial olean from a failed compile must not poison later imports
[ $EXIT_CODE -ne 0 ] && rm -f "$OLEAN_FILE"
exit $EXIT_CODE