archy/loop/loop.sh

#!/usr/bin/env sh
# Headless loop script for overnight Claude Code automation.
# Set CLAUDE_AUTONOMOUS=1 for Ralph Wiggum (Stop hook blocks until plan is complete).
# Rate-limit aware: detects limits, sleeps until reset, and retries automatically.
set -eu

PROJECT_DIR="${CLAUDE_PROJECT_DIR:-$(cd "$(dirname "$0")/.." && pwd)}"
PROMPT_FILE="${PROMPT_FILE:-$PROJECT_DIR/loop/prompt.md}"
LOG_FILE="${LOG_FILE:-$PROJECT_DIR/loop/loop.log}"
ITERATION_COUNT="${ITERATION_COUNT:-1}"
ITERATION_DELAY="${ITERATION_DELAY:-600}"
CLAUDE_BIN="${CLAUDE_BIN:-claude}"
RATE_LIMIT_WAIT="${RATE_LIMIT_WAIT:-3600}"  # Default: wait 1 hour on rate limit
MAX_RATE_LIMIT_RETRIES="${MAX_RATE_LIMIT_RETRIES:-5}"  # Max retries before giving up

cd "$PROJECT_DIR"

log() {
  echo "$1" | tee -a "$LOG_FILE"
}

# Check if plan has remaining tasks
plan_has_tasks() {
  grep -q '^\- \[ \]' "$PROJECT_DIR/loop/plan.md" 2>/dev/null
}

# Detect rate limit from Claude output
check_rate_limit() {
  # Check last 50 lines of log for rate limit indicators
  tail -50 "$LOG_FILE" 2>/dev/null | grep -qi \
    -e "rate.limit" \
    -e "too.many.requests" \
    -e "429" \
    -e "quota.exceeded" \
    -e "usage.limit" \
    -e "limit.reached" 2>/dev/null
}

log "=== Overnight loop started $(date '+%Y-%m-%dT%H:%M:%S' 2>/dev/null || date) ==="
log "  PROMPT_FILE=$PROMPT_FILE"
log "  CLAUDE_AUTONOMOUS=${CLAUDE_AUTONOMOUS:-0}"
log "  ITERATION_COUNT=$ITERATION_COUNT"
log "  RATE_LIMIT_WAIT=${RATE_LIMIT_WAIT}s"
log ""

i=1
rate_limit_retries=0
while [ "$i" -le "$ITERATION_COUNT" ]; do
  log "--- Iteration $i/$ITERATION_COUNT @ $(date '+%Y-%m-%dT%H:%M:%S' 2>/dev/null || date) ---"
  export CLAUDE_PROJECT_DIR="$PROJECT_DIR"
  export CLAUDE_AUTONOMOUS="${CLAUDE_AUTONOMOUS:-1}"

  # Run Claude with autonomous permissions; prompt from file
  if [ -f "$PROMPT_FILE" ]; then
    "$CLAUDE_BIN" -p --dangerously-skip-permissions --output-format=stream-json \
      < "$PROMPT_FILE" 2>&1 | tee -a "$LOG_FILE" || true
  else
    log "Error: $PROMPT_FILE not found"
    exit 1
  fi

  # Check for rate limit after Claude exits
  if check_rate_limit; then
    rate_limit_retries=$((rate_limit_retries + 1))
    if [ "$rate_limit_retries" -ge "$MAX_RATE_LIMIT_RETRIES" ]; then
      log "Rate limited $rate_limit_retries times — giving up."
      log "Scheduling retry via launchd..."

      # Schedule a retry using launchd for after rate limit resets
      PLIST_LABEL="com.aiui.overnight-retry"
      PLIST_PATH="$HOME/Library/LaunchAgents/${PLIST_LABEL}.plist"
      RETRY_TIME=$(date -v+${RATE_LIMIT_WAIT}S '+%H:%M' 2>/dev/null || date -d "+${RATE_LIMIT_WAIT} seconds" '+%H:%M')
      RETRY_HOUR=$(echo "$RETRY_TIME" | cut -d: -f1)
      RETRY_MIN=$(echo "$RETRY_TIME" | cut -d: -f2)

      cat > "$PLIST_PATH" <<PLIST
<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
<plist version="1.0">
<dict>
  <key>Label</key>
  <string>${PLIST_LABEL}</string>
  <key>ProgramArguments</key>
  <array>
    <string>/bin/sh</string>
    <string>-c</string>
    <string>cd ${PROJECT_DIR} && caffeinate -i ./loop/loop.sh >> ${LOG_FILE} 2>&1; launchctl unload ${PLIST_PATH}; rm -f ${PLIST_PATH}</string>
  </array>
  <key>StartCalendarInterval</key>
  <dict>
    <key>Hour</key>
    <integer>${RETRY_HOUR}</integer>
    <key>Minute</key>
    <integer>${RETRY_MIN}</integer>
  </dict>
  <key>EnvironmentVariables</key>
  <dict>
    <key>CLAUDE_AUTONOMOUS</key>
    <string>1</string>
    <key>CLAUDE_PROJECT_DIR</key>
    <string>${PROJECT_DIR}</string>
    <key>PATH</key>
    <string>/usr/local/bin:/usr/bin:/bin:$HOME/.local/bin</string>
  </dict>
  <key>StandardOutPath</key>
  <string>${LOG_FILE}</string>
  <key>StandardErrorPath</key>
  <string>${LOG_FILE}</string>
</dict>
</plist>
PLIST

      launchctl load "$PLIST_PATH" 2>/dev/null || true
      log "Scheduled retry at ~${RETRY_TIME} via launchd ($PLIST_PATH)"
      log "The plist auto-removes after running."
      exit 0
    fi

    log "Rate limit detected (attempt $rate_limit_retries/$MAX_RATE_LIMIT_RETRIES)."
    log "Sleeping ${RATE_LIMIT_WAIT}s until $(date -v+${RATE_LIMIT_WAIT}S '+%H:%M:%S' 2>/dev/null || date -d "+${RATE_LIMIT_WAIT} seconds" '+%H:%M:%S')..."
    sleep "$RATE_LIMIT_WAIT"

    # Check if plan still has tasks before retrying
    if ! plan_has_tasks; then
      log "All plan tasks completed during rate limit wait. Done."
      break
    fi
    log "Retrying after rate limit..."
    continue  # Retry same iteration
  fi

  # Reset rate limit counter on successful run
  rate_limit_retries=0

  i=$((i + 1))
  if [ "$i" -le "$ITERATION_COUNT" ] && [ "$ITERATION_DELAY" -gt 0 ]; then
    log "Waiting ${ITERATION_DELAY}s before next iteration..."
    sleep "$ITERATION_DELAY"
  fi
done

log "=== Loop complete $(date '+%Y-%m-%dT%H:%M:%S' 2>/dev/null || date) ==="