#!/bin/bash
# ============================================================================
# enrich_wave.sh — ONE throttled enrichment wave, fully headless (no Claude
# session). Designed to be run by the LXC's OS cron at night.
#
#   - Prepares a bounded wave (first N missing keys) via enrichment_wave.py.
#   - Runs ONE `claude -p` per batch file, PAR batches concurrently (OS-level
#     parallelism — no Workflow tool, no 2-per-workflow cap, no session needed).
#   - When the backlog is empty, runs --collect + --rebuild and stops.
#
# Throttle = --keys (default 700 ≈ 75% of a 5h usage window ≈ 950 keys).
# A single flock guarantees waves never overlap.
#
# Usage:  scripts/enrich_wave.sh [KEYS] [PAR]
#         KEYS = max keys this wave   (default 700)
#         PAR  = concurrent claude -p (default 6)
# ============================================================================
set -uo pipefail

REPO="/workspace/game-library"
LOG_DIR="/workspace/.claude-logs"
LOCK="/tmp/enrich_wave.lock"
KEYS="${1:-700}"
PAR="${2:-6}"
MAX_TURNS=100

# --- environment (cron has a minimal env) ---------------------------------- #
export HOME="${HOME:-/home/claude}"
[ -f "$HOME/.nvm/nvm.sh" ] && . "$HOME/.nvm/nvm.sh" >/dev/null 2>&1
export PATH="$HOME/.nvm/versions/node/v20.19.6/bin:/usr/local/bin:/usr/bin:/bin:$PATH"

mkdir -p "$LOG_DIR"
TS="$(date +%Y%m%d_%H%M%S)"
LOG="$LOG_DIR/enrich_${TS}.log"

log() { echo "[$(date '+%H:%M:%S')] $*" | tee -a "$LOG"; }

# --- single-instance lock: skip if a wave is still running ----------------- #
exec 9>"$LOCK"
if ! flock -n 9; then
  log "another wave holds the lock; exiting."
  exit 0
fi

cd "$REPO" || { log "cannot cd $REPO"; exit 1; }
command -v claude >/dev/null 2>&1 || { log "claude CLI not on PATH"; exit 1; }

log "=== enrichment wave start (keys=$KEYS par=$PAR) ==="

# --- 1) prepare bounded wave (batch files only) ---------------------------- #
PREP="$(python3 scripts/enrichment_wave.py --prepare --keys "$KEYS" --no-shards 2>&1)"
echo "$PREP" | tee -a "$LOG"

if echo "$PREP" | grep -q "WAVE: COMPLETE"; then
  log "backlog empty -> collect + rebuild"
  python3 scripts/run_enrichment.py --collect   >>"$LOG" 2>&1
  python3 scripts/build_database.py --rebuild   >>"$LOG" 2>&1
  grep -E "enrichment .*matched" "$LOG" | tail -1 | tee -a "$LOG"
  log "=== ENRICHMENT COMPLETE ==="
  exit 0
fi

# --- 2) per-batch headless enrichment, PAR-way parallel -------------------- #
read -r -d '' BATCH_PROMPT <<'EOP'
You are an enrichment subagent in the game-library pipeline. Working dir: /workspace/game-library.

Read `scripts/ENRICHMENT_PROMPT.md` FIRST — it defines the rules and output format EXACTLY (translate faithfully to Romanian; expand description_ro ONLY from the source chunk text; mark inferred filter fields in estimated_fields; fixed enum vocab).

Your batch file is __BATCHFILE__ — it lists content_keys, one per line. For EACH key:
1. IDEMPOTENT SKIP: if `data/enrichment_parts/<key>.json` already exists AND parses as valid JSON, SKIP it (do not rewrite).
2. Otherwise read its prompt `data/enrichment_prompts/<key>.prompt.md`, produce the enrichment JSON per ENRICHMENT_PROMPT.md, and write it to `data/enrichment_parts/<key>.json` (MUST include the exact "content_key": "<key>").
3. Validate it parses: python3 -c "import json;json.load(open('data/enrichment_parts/<key>.json'))".

CRITICAL — JSON quote escaping: any literal ASCII double-quote inside a string value MUST be escaped as \". Romanian text uses „cuvant" where the closing mark is a plain ASCII " — written raw it breaks the JSON. Either keep the typographic „ " marks or escape every ASCII ". Re-read and re-validate each file; fix any that fail.

Work through EVERY key in the batch file. If a key's prompt is missing, skip it and continue. When done, reply with one line: the count written and skipped.
EOP

export REPO LOG MAX_TURNS BATCH_PROMPT
run_one() {
  local bf="$1"
  local name; name="$(basename "$bf")"
  local prompt="${BATCH_PROMPT/__BATCHFILE__/$bf}"
  cd "$REPO" || return 1
  timeout 1200 claude -p "$prompt" \
    --allowedTools "Bash(python3:*),Read,Write,Bash(cat:*),Bash(ls:*)" \
    --max-turns "$MAX_TURNS" </dev/null >>"$LOG.$name.out" 2>&1
  echo "[$(date '+%H:%M:%S')] done $name (exit $?)" >>"$LOG"
}
export -f run_one

BATCHES=(data/enrichment_batches/batch_*.txt)
log "launching ${#BATCHES[@]} batches, $PAR concurrent..."
printf '%s\n' "${BATCHES[@]}" | xargs -P "$PAR" -I{} bash -c 'run_one "$@"' _ {}

# --- 3) summary ------------------------------------------------------------ #
if grep -qi "session limit\|usage limit" "$LOG".batch_*.out 2>/dev/null; then
  log "WINDOW EXHAUSTED (usage limit hit mid-wave) — unfinished keys retry next fire."
fi
STATUS="$(python3 scripts/enrichment_wave.py --status 2>&1 | grep -E 'good|missing|done')"
echo "$STATUS" | tee -a "$LOG"
log "=== wave done ==="