#!/usr/bin/env bash
# Crash-resilient full-scale generation supervisor.
#
# gen_synthetic.py now (a) streams each sample to disk the instant it's produced
# (O(workers) memory, not O(n)) and (b) supports --resume: it counts existing
# lines and only generates+appends the missing suffix. So a kill mid-run keeps
# all progress on disk; re-running --resume continues from where it stopped.
#
# This supervisor loops "run --resume -> check count" until the target line
# count is reached. If the supervisor itself is killed, the data already on
# disk survives; relaunch this script and it picks up. Convergence is guaranteed:
# every iteration that survives adds >= 1 line.
#
# Usage: scripts/gen_full_supervisor.sh
set -uo pipefail   # NB: no -e — a killed gen sub-call must NOT abort the loop
cd "$(dirname "$0")/.."
export PYTHONPATH=src
W=$(nproc)

gen() {  # target_n  out  seed  [extra flags...]
  local target=$1 out=$2 seed=$3; shift 3
  while :; do
    local cur=0
    if [ -f "$out" ]; then cur=$(wc -l < "$out"); fi
    if [ "$cur" -ge "$target" ]; then
      echo "[sup] $out done: $cur/$target lines"; return 0
    fi
    echo "[sup] $out at $cur/$target — launching --resume $(date '+%H:%M:%S')"
    .venv/bin/python scripts/gen_synthetic.py \
      --n "$target" --out "$out" --seed "$seed" --workers "$W" --resume "$@"
    # loop: re-check count (gen may have been killed or completed)
  done
}

echo "[sup] === START $(date '+%H:%M:%S') ==="
gen 500000 data/align.jsonl 0
gen 100000 data/sft.jsonl   0 --evolve
echo "[sup] === ALL DONE $(date '+%H:%M:%S') ==="
echo "[sup] align=$(wc -l < data/align.jsonl) sft=$(wc -l < data/sft.jsonl) eval=$(wc -l < data/eval_synth.jsonl)"