#!/usr/bin/env bash
# download-frank-dragoon-halogen.sh — fetch frank-dragoon's halogen payload:
# the qwen3.8-27b .hgn checkpoint and the export tokenizer, from the
# PUBLIC peonist-ai/halogen-qwen3.8-27b repo (no token — and per the fleet
# secret law, none would ever touch argv).
#
# The fetch law, same as every sibling script: curl -f (an access error
# must not become a "successful" 153-byte artifact), exact byte count from
# the model card, LFS sha256 verification, --verify-only to re-check an
# existing payload without downloading.
set -euo pipefail

DEST="${FRANK_DRAGOON_MODEL_DIR:-$HOME/models/halogen-qwen3.8-27b}"
BASE="https://huggingface.co/peonist-ai/halogen-qwen3.8-27b/resolve/main"

FILES=(qwen3.8-27b-p1w4d-d2.hgn
       tokenizer/tokenizer.json
       tokenizer/vocab.json
       tokenizer/merges.txt
       tokenizer/chat_template.jinja
       tokenizer/tokenizer_config.json)
# Byte sizes as published by the Hub on 2026-10-05, plus sha256 (the LFS
# oid) where the Hub stores an LFS object — plain git blobs carry no oid
# and are size-checked only. Re-check with:
# curl -s "https://huggingface.co/api/models/peonist-ai/halogen-qwen3.8-27b/tree/main?recursive=true"
SIZES=(35865565184 12809320 6722759 3353259 8952 17928)
SHAS=(274c3fc767fb57faf025dd03c76376b1fc1b32448aef45aaf02d1898fa962089
      0997f410c57a1f4e53b09e4be8f4a172d90edd9564368fb0847030937229b9f3 - - - -)

VERIFY_ONLY=0
[ "${1:-}" = "--verify-only" ] && VERIFY_ONLY=1

mkdir -p "$DEST"

for i in "${!FILES[@]}"; do
    f="${FILES[$i]}"; want="${SIZES[$i]}"; sha="${SHAS[$i]}"
    path="$DEST/$f"
    mkdir -p "$(dirname "$path")"
    if [ "$VERIFY_ONLY" -eq 0 ]; then
        # A file already at the published size skips the fetch entirely:
        # resuming it would ask the CDN for a range past EOF (416 -> curl
        # error under set -e), and re-pulling 33.4 GiB to prove a point is
        # not what --verify-only is for. sha256 below still decides.
        if [ -f "$path" ] && [ "$(stat -c %s "$path")" = "$want" ]; then
            echo "HAVE  $f ($want bytes) — skipping fetch"
        else
            echo "FETCH $f -> $path"
            # HF answers /resolve/ with a 302 to the Xet CDN and curl DROPS
            # the Range header across redirects — a naive -C - then
            # "resumes" by pulling the ~1 KB redirect body (measured
            # 2026-10-05: file frozen 14 MiB short, curl exit 0). Resolve
            # the effective URL first, then resume against the CDN, which
            # honors Range.
            url=$(curl -sfIL -o /dev/null -w '%{url_effective}' "$BASE/$f") \
                || { echo "cannot resolve $BASE/$f" >&2; exit 1; }
            curl -fL --retry 5 -C - -o "$path" "$url"
        fi
    fi
    [ -f "$path" ] || { echo "MISSING $path (run without --verify-only)" >&2; exit 1; }
    got="$(stat -c %s "$path")"
    [ "$got" = "$want" ] || { echo "SIZE $path: $got != $want" >&2; exit 1; }
    echo "OK   $f ($got bytes)"
done

echo "byte counts match; verifying sha256 where the Hub publishes an LFS oid..."
for i in "${!FILES[@]}"; do
    f="${FILES[$i]}"; sha="${SHAS[$i]}"
    if [ "$sha" = "-" ]; then
        echo "OK   $f (plain git blob, size-checked)"
        continue
    fi
    got="$(sha256sum "$DEST/$f" | cut -d' ' -f1)"
    [ "$got" = "$sha" ] || { echo "SHA256 $f: $got != $sha" >&2; exit 1; }
    echo "OK   $f sha256"
done
echo "DOWNLOAD_DONE $DEST"