#!/usr/bin/env bash
# Download the Q4_K_XL frank-dragoon payload on Dankclaw:
#   unsloth/Qwen3.8-27B-GGUF  ->  Qwen3.8-27B-UD-Q4_K_XL.gguf
#
#   bash scripts/download-frank-dragoon-q4.sh
#   bash scripts/download-frank-dragoon-q4.sh --verify-only
#
# Integrity: the file is checked against its declared byte count and sha256
# (the LFS oid from the Hub tree API, 2026-10-01). NO AUTH HEADER IS USED:
# the repo is public and ungated (gated: false), and a token on the curl
# command line is world-readable via /proc/<pid>/cmdline. If this ever needs
# a token, put it in a mode-600 file and pass it with `curl -K`.
#
# Layout after a successful run (MODEL_DIR):
#   Qwen3.8-27B-UD-Q4_K_XL.gguf   17559178144  (16.35 GiB)
#
# WHY Q4 AND NOT THE Q8 SWIFT PAYLOAD: this is the vanilla (non-abliterated)
# Qwen3.8-27B at UD-Q4_K_XL, ~13 GiB smaller than the Swift UD-Q8_K_XL. Every
# GiB of weights saved is a GiB of f16 KV the endpoint can hold instead: the
# KV costs 64 KiB/token (16 full-attention layers x 4 KV heads x 256 head_dim
# x 2 (K,V) x 2 B), so 4 sessions x 163840 ctx = 640,000 tokens = 39.06 GiB.
#
# The speculative drafter is UNCHANGED and still fetched by its own script
# (scripts/download-frank-dragoon.sh, z-lab's Hub repo). That name must not
# appear here at all — the frank-dragoon seam greps THIS file for it to prove
# the drafter was not folded into the payload fetch.
#
# NOTE ON MTP: this payload has no baked-in MTP head (the Hub repo ships one
# separately as MTP/mtp-Qwen3.8-27B-Q4_0.gguf). frank-dragoon does not need it —
# spec decode here is the block-diffusion drafter, not MTP.
set -euo pipefail

MODEL_DIR="/home/dank/models/Qwen3.8-27B-UD-Q4_K_XL"
REL="Qwen3.8-27B-UD-Q4_K_XL.gguf"
SIZE=17559178144
SHA=3f227079003add2511437e5b1e94812e363385225bf6a9b47b0054a72bc8b01e
URL="https://huggingface.co/unsloth/Qwen3.8-27B-GGUF/resolve/main/${REL}"

mode="download"
[[ "${1:-}" == "--verify-only" ]] && mode="verify"

if [[ "$mode" == "download" ]]; then
    mkdir -p "$MODEL_DIR"
    if [[ -s "$MODEL_DIR/$REL" ]]; then
        echo "already present: $MODEL_DIR/$REL"
    else
        echo "fetching $REL (17559178144 bytes) — this is ~16.4 GiB"
        # -f so an HTTP error is a failure, not a 153-byte "artifact".
        # -C - so an interrupted run resumes instead of restarting.
        curl -fL -C - --retry 5 --retry-delay 3 -o "$MODEL_DIR/$REL" "$URL"
    fi
fi

echo "verifying $MODEL_DIR against declared size + sha256"
python3 - "$MODEL_DIR" "$REL" "$SIZE" "$SHA" <<'PY'
import hashlib, os, sys
model_dir, rel, size, sha = sys.argv[1], sys.argv[2], int(sys.argv[3]), sys.argv[4]
dest = os.path.join(model_dir, rel)
if not os.path.isfile(dest):
    print(f"  MISSING {rel}")
    sys.exit(1)
actual = os.path.getsize(dest)
if actual != size:
    print(f"  SIZE MISMATCH {rel}: {actual} != {size}")
    sys.exit(1)
h = hashlib.sha256()
with open(dest, "rb") as f:
    for chunk in iter(lambda: f.read(1 << 24), b""):
        h.update(chunk)
if h.hexdigest() != sha:
    print(f"  SHA256 MISMATCH {rel}: {h.hexdigest()}")
    sys.exit(1)
print(f"  OK {rel} ({actual} bytes, sha256 matches the Hub LFS oid)")
PY

echo "Q4_K_XL payload complete: $MODEL_DIR"