#!/usr/bin/env bash
# download-frank-dragoon-flashnext.sh — fetch frank-dragoon's flash-server v2
# payload: the Quat3rnion abliterated Swift1.5 checkpoint of peonist's v2
# .hgn, the REQUIRED lookup table and the optional vision tower from
# peonist-ai/halogen-qwen3.8-flash-next (both at the revisions the model
# card pins), and the flat tokenizer the two repos share. All public, 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 Hub tree API, LFS sha256 verification, --verify-only to re-check an
# existing payload without downloading.
#
# File manifest (verified against the Hub tree API on 2026-10-06):
#   qwen38-flash-next-v2-swift15-abliterated.hgn  66,687,678,464 B  sha256
#     9c880b8ba48deabfa06172eff1e7572e4fe465e09e97faec6e50c3f6fdcac037
#     (Quat3rnion main; compacted r2 of the card's 89,775,868,032 B
#     append-only original — byte-identical live tensors, dropped padding)
#   qwen38-flash-next-ngram.hgn  51,200,246,144 B  sha256
#     3450acada94e19aabad88bd49b45eb70304820949c2240fc178067b20ae5dffe
#     (peonist @5cc17cea; REQUIRED — the engine reads it beside the
#     checkpoint)
#   qwen38-flash-next-vision.hgn  897,916,416 B  sha256
#     d62e0ae553fe88afd3833733d4a4c669f34d20fd8dfce4b9610525bed2134b10
#     (peonist @e053f488; optional, enables image input)
#   tokenizer/* @e053f488 — byte-identical to the 27B-era tokenizer
#     already on disk (tokenizer.json LFS
#     0997f410c57a1f4e53b09e4be8f4a172d90edd9564368fb0847030937229b9f3);
#     fetched fresh rather than symlinked, per the no-symlink law.
set -euo pipefail

DEST="${FRANK_DRAGOON_MODEL_DIR:-$HOME/models/halogen-flashnext-v2}"
ABLIT="https://huggingface.co/Quat3rnion/halogen-swift1.5-qwen3.8-flash-next-v2-abliterated/resolve/main"
PEONIST="https://huggingface.co/peonist-ai/halogen-qwen3.8-flash-next/resolve"
NGRAM_REV="5cc17cea1a10b502b4a5db41d8d2b1a0f22dba26"
TOK_REV="e053f488b120b99ed2525e6ac99f68c51b3b6179"

FILES=(qwen38-flash-next-v2-swift15-abliterated.hgn
       qwen38-flash-next-ngram.hgn
       qwen38-flash-next-vision.hgn
       tokenizer/tokenizer.json
       tokenizer/chat_template.jinja
       tokenizer/generation_config.json
       tokenizer/merges.txt
       tokenizer/vocab.json
       tokenizer/tokenizer_config.json)
SIZES=(66687678464
       51200246144
       897916416
       12809320
       8952
       202
       3353259
       6722759
       17928)
SHAS=(9c880b8ba48deabfa06172eff1e7572e4fe465e09e97faec6e50c3f6fdcac037
      3450acada94e19aabad88bd49b45eb70304820949c2240fc178067b20ae5dffe
      d62e0ae553fe88afd3833733d4a4c669f34d20fd8dfce4b9610525bed2134b10
      0997f410c57a1f4e53b09e4be8f4a172d90edd9564368fb0847030937229b9f3
      - - - - - -)

# Fetch source per file: repo base + revision (empty = ABLIT @main).
SRCS=("$ABLIT"
      "$PEONIST/$NGRAM_REV"
      "$PEONIST/$TOK_REV"
      "$PEONIST/$TOK_REV"
      "$PEONIST/$TOK_REV"
      "$PEONIST/$TOK_REV"
      "$PEONIST/$TOK_REV"
      "$PEONIST/$TOK_REV"
      "$PEONIST/$TOK_REV")

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[$i]}"; base="${SRCS[$i]}"
    path="$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 62 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 -> $path"
            # HF answers /resolve/ with a 302 to the Xet CDN and curl DROPS
            # the Range header across redirects — a naive -C - then
            # "resumes" by pulling the ~1 KB redirect body (measured
            # 2026-10-05 on the 27B fetch: file frozen 14 MiB short, curl
            # exit 0). Resolve the effective URL first, then resume
            # against the CDN, which honors Range.
            url=$(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"