feat(skills): machine-wide gate for heavy test runs

Parallel yolo/nightshift/blitz sessions each ran the full suite and OOMed the box. gate.sh caps concurrency, memory and build parallelism; skills now run scoped checks in the loop and one gated full run per push. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_015YUXS63P1WCdC6bEKWcnAE
2026-07-27 12:41:03 +00:00
parent c8de8bcb5a
commit 999f759691
6 changed files with 167 additions and 10 deletions
@@ -0,0 +1,101 @@
+#!/usr/bin/env bash
+# Machine-wide semaphore for heavy verification (test suites, builds).
+# Many autonomous sessions share one box; without this they all run the full
+# suite at once and OOM the machine. Exit 75 means "did not run, hand to CI".
+set -uo pipefail
+
+LOCKDIR="${AGENT_GATE_DIR:-${XDG_RUNTIME_DIR:-/tmp}/agent-gate}"
+SLOTS="${AGENT_GATE_SLOTS:-}"
+WAIT="${AGENT_GATE_WAIT:-600}"
+MEM_FLOOR_MB="${AGENT_GATE_MEM_FLOOR:-2000}"
+MEM_MAX="${AGENT_GATE_MEM_MAX:-3G}"
+CPU_QUOTA="${AGENT_GATE_CPU_QUOTA:-}"
+JOBS="${AGENT_GATE_JOBS:-}"
+
+cores=$(nproc 2>/dev/null || echo 4)
+[ -n "$SLOTS" ] || SLOTS=$(( cores / 4 )); [ "$SLOTS" -lt 1 ] && SLOTS=1
+[ -n "$JOBS" ] || JOBS=$(( cores / SLOTS / 2 )); [ "$JOBS" -lt 1 ] && JOBS=1
+[ -n "$CPU_QUOTA" ] || CPU_QUOTA="$(( JOBS * 100 ))%"
+
+avail_mb() { awk '/MemAvailable/ {print int($2/1024); exit}' /proc/meminfo 2>/dev/null || echo 99999; }
+
+usage() {
+  cat <<'EOF'
+gate.sh — run a heavy command under a machine-wide concurrency + memory cap.
+
+  gate.sh [-w SECS] [-s SLOTS] [-m MEMMAX] -- <command...>
+  gate.sh --status
+
+Exit codes: command's own status, or 75 if no slot / not enough free RAM
+within the wait budget (caller should skip the check and let CI cover it).
+
+Env: AGENT_GATE_SLOTS AGENT_GATE_WAIT AGENT_GATE_MEM_FLOOR
+     AGENT_GATE_MEM_MAX AGENT_GATE_CPU_QUOTA AGENT_GATE_JOBS AGENT_GATE_DIR
+EOF
+}
+
+status() {
+  mkdir -p "$LOCKDIR"
+  local free=0 busy=0 i
+  for i in $(seq 1 "$SLOTS"); do
+    if flock -n "$LOCKDIR/slot.$i" true 2>/dev/null; then free=$((free+1)); else busy=$((busy+1)); fi
+  done
+  echo "slots: $busy busy / $SLOTS total (${free} free)"
+  echo "mem:   $(avail_mb) MB available (floor ${MEM_FLOOR_MB} MB)"
+  [ -s "$LOCKDIR/holders" ] && { echo "recent holders:"; tail -5 "$LOCKDIR/holders"; }
+  return 0
+}
+
+while [ $# -gt 0 ]; do
+  case "$1" in
+    -w|--wait) WAIT="$2"; shift 2 ;;
+    -s|--slots) SLOTS="$2"; shift 2 ;;
+    -m|--mem-max) MEM_MAX="$2"; shift 2 ;;
+    --status) status; exit 0 ;;
+    -h|--help) usage; exit 0 ;;
+    --) shift; break ;;
+    *) break ;;
+  esac
+done
+[ $# -gt 0 ] || { usage; exit 2; }
+
+mkdir -p "$LOCKDIR"
+deadline=$(( $(date +%s) + WAIT ))
+fd=""
+
+while :; do
+  if [ "$(avail_mb)" -ge "$MEM_FLOOR_MB" ]; then
+    for i in $(seq 1 "$SLOTS"); do
+      exec {try}>"$LOCKDIR/slot.$i"
+      if flock -n "$try"; then fd="$try"; break; fi
+      exec {try}>&-
+    done
+  fi
+  [ -n "$fd" ] && break
+  left=$(( deadline - $(date +%s) ))
+  [ "$left" -le 0 ] && {
+    echo "gate: no slot within ${WAIT}s (avail $(avail_mb) MB) — skipping, CI covers this" >&2
+    exit 75
+  }
+  sleep $(( left < 10 ? left : 10 ))
+done
+
+echo "$(date -Iseconds) pid=$$ cwd=$PWD cmd=$*" >>"$LOCKDIR/holders"
+
+export CARGO_BUILD_JOBS="$JOBS" RUST_TEST_THREADS="$JOBS" \
+       VITEST_MAX_THREADS="$JOBS" VITEST_MAX_FORKS="$JOBS" \
+       MAKEFLAGS="-j$JOBS" GOMAXPROCS="$JOBS" \
+       NODE_OPTIONS="${NODE_OPTIONS:-} --max-old-space-size=2048"
+
+if command -v systemd-run >/dev/null 2>&1 && \
+   systemd-run --user --scope -q -p MemoryMax=64M true >/dev/null 2>&1; then
+  systemd-run --user --scope -q --collect \
+    -p "MemoryMax=$MEM_MAX" -p "MemorySwapMax=0" -p "CPUQuota=$CPU_QUOTA" \
+    -- "$@"
+else
+  "$@"
+fi
+rc=$?
+
+exec {fd}>&-
+exit $rc