#!/usr/bin/env bash
# Chained after the instruct probe: run the tests that decide whether it worked.
#
# ⚠ PICKS THE BEST CHECKPOINT, not the end-of-run adapter. 4B-Base turned at step 75
# and its shipped adapter was the WORSE weights; that cost a re-cut. Applying the
# lesson: read loss-series.json, take the argmin, and say which one was chosen.
#
# Four arms, and the CONTROL is the one that makes the rest readable:
#   1. tuned  + chat template  -- did instruction-following SURVIVE the training?
#   2. UNTUNED + chat template -- the control. Panel B used the 27B gen seat, so
#      without a 4B control any degradation is unattributable between "the adapter
#      broke it" and "a 4B is just weaker at this than a 27B".
#   3. tuned  + raw continuation, the 9 voice prompts -- comparable to every rung.
#   4. tuned  + the plot-furniture prompts -- the operator's point that a completion
#      carrier reaches for Brontë's devices instead of Skaldsong's. If the instruct
#      prior resists the gloom-override, that shows up here.
set -uo pipefail
PREV=/home/infra-ops/r49-runs/h02-4b-instruct-1ep
OUT=/home/infra-ops/r49-runs/instruct-probe
V=/home/infra-ops/ml/.venv/bin/python
BASE=/home/infra-ops/carriers/Qwen3-4B-Instruct
exec >> /home/infra-ops/r49-runs/chain-instruct-probe.log 2>&1
echo "=== $(date -Is) armed, waiting on $PREV"
while [ -f "$PREV/run.pid" ] && kill -0 "$(cat "$PREV/run.pid")" 2>/dev/null; do sleep 60; done
echo "=== $(date -Is) training finished"
[ -f "$PREV/adapter/adapter_model.safetensors" ] || { echo "=== REFUSING: no adapter"; exit 1; }

CK=$($V - <<'PY'
import json
d = json.load(open("/home/infra-ops/r49-runs/h02-4b-instruct-1ep/loss-series.json"))
rows = [(r["step"], r["eval_loss"]) for r in
        (d if isinstance(d, list) else d.get("log_history", d.get("series", [])))
        if isinstance(r, dict) and r.get("eval_loss") is not None]
best = min(rows, key=lambda r: r[1])
import os
p = f"/home/infra-ops/r49-runs/h02-4b-instruct-1ep/checkpoints/checkpoint-{best[0]}"
print(p if os.path.isdir(p) else "/home/infra-ops/r49-runs/h02-4b-instruct-1ep/adapter")
PY
)
echo "=== best checkpoint selected: $CK"
cd /home/infra-ops/r49-prep
$V gen_beats_chat.py --base "$BASE" --adapter "$CK" --beats beats.json --arm instruct-tuned-chat --out "$OUT/tuned-chat.jsonl"
$V gen_beats_chat.py --base "$BASE"                  --beats beats.json --arm instruct-untuned-chat --out "$OUT/untuned-chat.jsonl"
$V gen_voice_test.py --base "$BASE" --adapter "$CK" --arm instruct-tuned --prompts voice_prompts.json --out "$OUT/voice.jsonl"
for pf in abernathy.json letter.json; do
  $V gen_voice_test.py --base "$BASE" --adapter "$CK" --arm instruct-tuned \
     --prompts "$pf" --seeds 1234 5678 4242 --max-new-tokens 320 \
     --out "$OUT/${pf%.json}.jsonl"
done
echo "=== $(date -Is) instruct probe arms written to $OUT"