#!/usr/bin/env bash
# kld-gate-swift15.sh — RUNS ON DANKSERVER. Score the quantized candidate
# against the BF16 reference and apply the pre-approved gate:
#   mean KL <= 0.03 AND top-1 agreement >= 95%.
# Same engine (1.0.13) and same boot shape as the reference RECORD
# (run-swift15-bf16.sh kld): disk-tier, no speculation, deterministic, fp8 KV.
# --kld-ref reads its tokens from the reference (no --kld-corpus here — the
# (run-swift15-bf16.sh kld): 1.0.13, tp 2, disk-tier, fp8 KV, no speculation,
# deterministic, max-model-len 16384, vram-kv 3072, 4 slots. Two deviations
# are forced by the w4 file: MNBT 2048 (the w4 kernels stream from the file
# tier ONLY at MNBT<=2048 — at the recording's 32768 the engine demands a
# widened form: "DID NOT FIT ... stored form is not the container's"), and
# pool 40960 (the recording's 12 GiB pool predates the w4 tables; at 12288 the
# gate_up slab cannot be cached). Chunk size is softmax-invariant, so the
# MNBT delta is float-order noise riding on the KL floor.
set -uo pipefail
PIN=sha256:4c3f484564bb2872784e46b0a59cbd71becc9c1e746e301a3596ffae253c322e
C=swift15gate
LOG=/home/dank/logs/swift15_kldgate.log
KLD_REF_DIR=/home/dank/corpora/kld-ref
KLD_OUT=/home/dank/radiance-state/kld-gate.json

[ -d "$KLD_REF_DIR" ] || { echo "missing reference: $KLD_REF_DIR"; exit 2; }
: > "$KLD_OUT"
cp -f /home/dank/serverAppConfigs/scripts/qwen38-froggeric-v22.5.jinja \
      /home/dank/models/tpl.jinja 2>/dev/null || true
sudo systemctl stop frank-primary >/dev/null 2>&1 || true
podman rm -f "$C" >/dev/null 2>&1 || true

podman run --rm --name "$C" \
    --network host --init \
    --security-opt seccomp=unconfined \
    --ulimit memlock=-1:-1 \
    --device /dev/kfd --device /dev/dri \
    -v /home/dank/models:/models:ro \
    -v /home/dank/radiance-state:/data \
    -v "$KLD_REF_DIR:/data/kld-ref:ro" \
    "stilldeadcode/radiance@$PIN" \
    --model /models/rad/qwen4exp-swift15-w4dn8-i8-hc8m.rad \
    --tp 2 --placement expert_tiered --weights-disk-tier \
    --host-pool-mib 40960 --deterministic --gpu-headroom-mib 768 \
    --num-speculative-tokens 0 \
    --kv-cache-dtype fp8 --max-model-len 16384 \
    --ngram-placement ram \
    --override-chat-template /models/tpl.jinja \
    --kld-ref /data/kld-ref --kld-out /data/kld-gate.json \
    --vram-kv-mib 3072 \
    --max-num-seqs 4 --max-num-batched-tokens 2048 \
    2>&1 | tee "$LOG"
rc=${PIPESTATUS[0]}
[ "$rc" -eq 0 ] || { echo "KLD GATE BOOT FAILED rc=$rc; log: $LOG"; exit "$rc"; }

python3 - "$KLD_OUT" "$LOG" <<'PY'
import json, sys, re
out, log = sys.argv[1], sys.argv[2]
def num(pat):
    m = re.findall(pat, open(log, errors="replace").read(), re.I)
    return float(m[-1]) if m else None
kl = top1 = None
try:
    d = json.load(open(out))
    def find(obj, keys):
        if isinstance(obj, dict):
            for k, v in obj.items():
                if any(s in k.lower() for s in keys) and isinstance(v, (int, float)):
                    return float(v)
            for v in obj.values():
                r = find(v, keys)
                if r is not None: return r
        return None
    kl = find(d, ("mean_kl", "mean kl", "kl_mean", "mean"))
    top1 = find(d, ("top1", "top_1", "top-1", "agreement"))
    if top1 is not None and top1 <= 1.0:
        top1 *= 100.0
except Exception as e:
    print("report JSON unusable (%s); falling back to log" % e)
if kl is None:
    kl = num(r"mean[_ ]kl[^0-9]*([0-9]*\.?[0-9]+(?:e[-+][0-9]+)?)")
if top1 is None:
    top1 = num(r"top[-_ ]?1[^0-9]*([0-9]*\.?[0-9]+)")
if kl is None or top1 is None:
    print("KLD GATE PARSE FAILED: mean_kl=%s top1=%s — inspect %s / %s" % (kl, top1, out, log))
    sys.exit(2)
print("KLD GATE: mean KL = %.4f (max 0.03) | top-1 = %.2f%% (min 95.0)" % (kl, top1))
ok = (kl <= 0.03) and (top1 >= 95.0)
print("KLD GATE " + ("PASS" if ok else "FAIL"))
sys.exit(0 if ok else 1)
PY
gate=$?
echo "kld-gate complete rc=$gate; log: $LOG report: $KLD_OUT"
exit "$gate"