#!/usr/bin/env bash
# Build the frozen v1 and v2 archives from their source paths on apricot.
# (v0 is built separately by cache-v0.sh because its source is on NFS.)
#
# Output:   .archive/platform.{1,2}.tar.zst
# Excludes: ML model weights, training data, build artifacts, vcs cruft.
#           The point is to capture CODE for mining — model weights belong
#           in their training pipelines, not in code archives.

set -euo pipefail

REPO_ROOT="$(cd "$(dirname "$0")/.." && pwd)"
ARCHIVE_DIR="$REPO_ROOT/.archive"
mkdir -p "$ARCHIVE_DIR"

EXCLUDES=(
    # vcs / build
    --exclude='.git'
    --exclude='.gitlab-ci-local'
    --exclude='.playwright-mcp'
    --exclude='.turbo'
    --exclude='.next'
    --exclude='dist'
    --exclude='build'
    --exclude='out'

    # package manager
    --exclude='node_modules'
    --exclude='.pnpm-store'
    --exclude='.yarn/cache'
    --exclude='.cache'

    # ML model directories (by convention) — superseded by @applications/@{ai,ml,imajin}
    --exclude='ml-service'
    --exclude='models'
    --exclude='checkpoints'
    --exclude='weights'
    --exclude='training/data'
    --exclude='training_data'
    --exclude='captcha-solver'

    # ML model files (anywhere)
    --exclude='*.gguf'
    --exclude='*.safetensors'
    --exclude='*.bin'
    --exclude='*.ckpt'
    --exclude='*.pth'
    --exclude='*.pt'
    --exclude='*.onnx'
    --exclude='*.h5'

    # large media
    --exclude='*.mp4'
    --exclude='*.mov'
    --exclude='*.webm'
    --exclude='*.zip'
    --exclude='*.tar.gz'
    --exclude='*.tar.zst'
)

ZSTD_LEVEL="${ZSTD_LEVEL:-3}"

build_archive() {
    local version="$1"
    local src_dir="$2"
    local src_parent
    local src_name
    src_parent="$(dirname "$src_dir")"
    src_name="$(basename "$src_dir")"

    local out="$ARCHIVE_DIR/${version}.tar.zst"

    if [ -f "$out" ]; then
        echo "skip ${version}: ${out} already exists (remove to rebuild)"
        return
    fi
    if [ ! -d "$src_dir" ]; then
        echo "skip ${version}: source not found at ${src_dir}"
        return
    fi

    echo
    echo "==> building ${version}  ←  ${src_dir}"
    echo "    output: ${out}"
    local before
    before=$(date +%s)
    tar "${EXCLUDES[@]}" -cf - -C "$src_parent" "$src_name" \
        | zstd -"$ZSTD_LEVEL" -T0 -o "$out"
    local after
    after=$(date +%s)
    local size
    size=$(du -h "$out" | cut -f1)
    echo "    done in $((after - before))s, size: ${size}"
}

build_archive "platform.1" "$HOME/Code/@projects/@lilith/lilith-platform"
build_archive "platform.2" "$HOME/Code/@projects/@lilith/lilith-platform.live"

echo
echo "built archives:"
ls -lh "$ARCHIVE_DIR"/*.tar.zst 2>/dev/null || true