#!/usr/bin/env bash
# download-frank-dragoon-v2abl.sh — fetch frank-dragoon's replacement payload:
# the CURRENT native-v2 abliterated checkpoint from
# Quat3rnion/halogen-qwen3.8-flash-next-v2-abliterated (the 2026-10-11
# release: a complete HIP native-v2 conversion of orcarouter's pinned BF16
# source, NOT the r1/r2 writer transplant this filename used to carry), and
# assemble the companions the engine needs beside it — the REQUIRED n-gram
# lookup table, the vision tower and the flat tokenizer. Public files, no
# token; 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
# script's manifest, LFS sha256 verification, --verify-only to re-check an
# existing payload without downloading.
#
# COMPANION LAW (read this before shipping the new checkpoint): the current
# release publishes ONLY the main file. Its card states plainly that the
# interchangeability of the stock peonist companions with this native
# conversion "has NOT been established" — the source-derived n-gram would be
# 51,200,246,084 B while peonist's stock table is 51,200,246,144 B (60 B
# apart, so whole-file identity cannot be assumed), and the source-derived
# vision file is the same size as stock but equal size is not proof of equal
# content. The six tokenizer assets ARE published with matching blob
# identities. No source-matched n-gram/vision pair is published anywhere, so
# the only companions available are peonist's — which is also what the
# historical r2 recipe pinned, and what the engine's own table-mismatch
# check gets to judge at boot. This script therefore hardlinks the verified
# peonist trio (a hardlink is a REGULAR file, so the serve gate's
# no-symlink law holds and 47.7 GiB is not copied), verifies every byte, and
# leaves the verdict to the boot ledger plus the behavior probes.
#
# File manifest (Quat3rnion @main, verified against the Hub API on
# 2026-10-18):
#   qwen38-flash-next-v2-abliterated.hgn  66,687,678,432 B  sha256
#     b5bd925fa2b44343be4a2cd328cae6b57ce7ffa2fe2cc56281717377e5a1ce8a
#   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 on the engine, enabled here for vision)
#   tokenizer/* @e053f488 — the six assets the two repos share.
set -euo pipefail

DEST="${FRANK_DRAGOON_MODEL_DIR:-$HOME/models/halogen-v2-abliterated}"
# Where the already-verified peonist companions live (the swift15-era dir).
DONOR="${FRANK_DRAGOON_DONOR_DIR:-$HOME/models/halogen-flashnext-v2}"
V2ABL="https://huggingface.co/Quat3rnion/halogen-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-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=(66687678432
       51200246144
       897916416
       12809320
       8952
       202
       3353259
       6722759
       17928)
SHAS=(b5bd925fa2b44343be4a2cd328cae6b57ce7ffa2fe2cc56281717377e5a1ce8a
      3450acada94e19aabad88bd49b45eb70304820949c2240fc178067b20ae5dffe
      d62e0ae553fe88afd3833733d4a4c669f34d20fd8dfce4b9610525bed2134b10
      0997f410c57a1f4e53b09e4be8f4a172d90edd9564368fb0847030937229b9f3
      - - - - - -)

# Fetch source per file: repo base + revision (first entry = V2ABL @main).
SRCS=("$V2ABL"
      "$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 ] && [ ! -f "$path" ] && [ -f "$DONOR/$f" ]; then
        # Companion reuse: a hardlink costs no disk and no copy, and stays a
        # regular file for the serve gate. Only the sha256 below decides.
        if [ "$(stat -c %s "$DONOR/$f")" = "$want" ]; then
            ln "$DONOR/$f" "$path"
            echo "LINK  $f from $DONOR (hardlink, $want bytes)"
        fi
    fi
    if [ "$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 -> $path"
            # HF answers /resolve/ with a 302 to the Xet CDN and curl DROPS
            # the Range header across redirects — a naive -C - then
            # "resumes" by pulling the ~1 KB redirect body. Resolve the
            # effective URL first, then resume against the CDN, which
            # honors Range.
            url=$(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 $path (run without --verify-only)" >&2; exit 1; }
    if [ -L "$path" ]; then
        echo "SYMLINK $path — the serve gate refuses symlinks; replace with a real file" >&2
        exit 1
    fi
    got="$(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"