#!/usr/bin/env bash
# Fig-18 naive nondeterminism: after the main pair (ABLATION12_DONE) finishes, run
# 2 more naive arms (runs 2 and 3) on the SAME substrate. The naive LLM (gpt-5.4,
# use_harness=false) is nondeterministic, so the run-to-run spread (fail / slow /
# lucky) is the result. Harness arm stays a single deterministic curve. Run from
# the repo root on dash1; survives disconnect via setsid/nohup at launch.
set -u
export OPENAI_API_KEY=$(python3 -c 'import json,pathlib;print(json.load(open(pathlib.Path.home()/".codex/auth.json"))["OPENAI_API_KEY"])')
export http_proxy= https_proxy= all_proxy= HTTP_PROXY= HTTPS_PROXY= ALL_PROXY= no_proxy='*'

# Wait for the main harness+naive(run1) pair to complete so we never contend for GPUs.
echo "=== waiting for ABLATION12_DONE $(date -Is) ==="
while [ ! -f .aituner/ABLATION12_DONE ]; do sleep 120; done
echo "=== main pair done, starting naive repeats $(date -Is) ==="

for r in 2 3; do
  rm -rf ".aituner/abl12-naive${r}" ".aituner/abl12-naive${r}.log"
  echo "=== naive run ${r} start $(date -Is) ==="
  PYTHONPATH=src python3 -m aituner.cli study tune \
    --spec configs/examples/dash0_qwen27b_ablation_naive_off.json \
    --store-root ".aituner/abl12-naive${r}" --max-trials 12 --skip-baseline > ".aituner/abl12-naive${r}.log" 2>&1
  echo "=== naive run ${r} done  $(date -Is) ==="
done

touch .aituner/NAIVE_REPEATS_DONE
echo "=== all naive repeats done $(date -Is) ==="