llmx/llmx-cli/scripts/build_npm_package.py

#!/usr/bin/env python3
"""Stage and optionally package the @valknar/llmx npm module."""

import argparse
import json
import shutil
import subprocess
import sys
import tempfile
from pathlib import Path

SCRIPT_DIR = Path(__file__).resolve().parent
CODEX_CLI_ROOT = SCRIPT_DIR.parent
REPO_ROOT = CODEX_CLI_ROOT.parent
RESPONSES_API_PROXY_NPM_ROOT = REPO_ROOT / "llmx-rs" / "responses-api-proxy" / "npm"
CODEX_SDK_ROOT = REPO_ROOT / "sdk" / "typescript"

PACKAGE_NATIVE_COMPONENTS: dict[str, list[str]] = {
    "llmx": ["llmx", "rg"],
    "llmx-responses-api-proxy": ["llmx-responses-api-proxy"],
    "llmx-sdk": ["llmx"],
}
COMPONENT_DEST_DIR: dict[str, str] = {
    "llmx": "llmx",
    "llmx-responses-api-proxy": "llmx-responses-api-proxy",
    "rg": "path",
}


def parse_args() -> argparse.Namespace:
    parser = argparse.ArgumentParser(description="Build or stage the LLMX CLI npm package.")
    parser.add_argument(
        "--package",
        choices=("llmx", "llmx-responses-api-proxy", "llmx-sdk"),
        default="llmx",
        help="Which npm package to stage (default: codex).",
    )
    parser.add_argument(
        "--version",
        help="Version number to write to package.json inside the staged package.",
    )
    parser.add_argument(
        "--release-version",
        help=(
            "Version to stage for npm release."
        ),
    )
    parser.add_argument(
        "--staging-dir",
        type=Path,
        help=(
            "Directory to stage the package contents. Defaults to a new temporary directory "
            "if omitted. The directory must be empty when provided."
        ),
    )
    parser.add_argument(
        "--tmp",
        dest="staging_dir",
        type=Path,
        help=argparse.SUPPRESS,
    )
    parser.add_argument(
        "--pack-output",
        type=Path,
        help="Path where the generated npm tarball should be written.",
    )
    parser.add_argument(
        "--vendor-src",
        type=Path,
        help="Directory containing pre-installed native binaries to bundle (vendor root).",
    )
    return parser.parse_args()


def main() -> int:
    args = parse_args()

    package = args.package
    version = args.version
    release_version = args.release_version
    if release_version:
        if version and version != release_version:
            raise RuntimeError("--version and --release-version must match when both are provided.")
        version = release_version

    if not version:
        raise RuntimeError("Must specify --version or --release-version.")

    staging_dir, created_temp = prepare_staging_dir(args.staging_dir)

    try:
        stage_sources(staging_dir, version, package)

        vendor_src = args.vendor_src.resolve() if args.vendor_src else None
        native_components = PACKAGE_NATIVE_COMPONENTS.get(package, [])

        if native_components:
            if vendor_src is None:
                components_str = ", ".join(native_components)
                raise RuntimeError(
                    "Native components "
                    f"({components_str}) required for package '{package}'. Provide --vendor-src "
                    "pointing to a directory containing pre-installed binaries."
                )

            copy_native_binaries(vendor_src, staging_dir, native_components)

        if release_version:
            staging_dir_str = str(staging_dir)
            if package == "llmx":
                print(
                    f"Staged version {version} for release in {staging_dir_str}\n\n"
                    "Verify the CLI:\n"
                    f"    node {staging_dir_str}/bin/llmx.js --version\n"
                    f"    node {staging_dir_str}/bin/llmx.js --help\n\n"
                )
            elif package == "llmx-responses-api-proxy":
                print(
                    f"Staged version {version} for release in {staging_dir_str}\n\n"
                    "Verify the responses API proxy:\n"
                    f"    node {staging_dir_str}/bin/llmx-responses-api-proxy.js --help\n\n"
                )
            else:
                print(
                    f"Staged version {version} for release in {staging_dir_str}\n\n"
                    "Verify the SDK contents:\n"
                    f"    ls {staging_dir_str}/dist\n"
                    f"    ls {staging_dir_str}/vendor\n"
                    "    node -e \"import('./dist/index.js').then(() => console.log('ok'))\"\n\n"
                )
        else:
            print(f"Staged package in {staging_dir}")

        if args.pack_output is not None:
            output_path = run_npm_pack(staging_dir, args.pack_output)
            print(f"npm pack output written to {output_path}")
    finally:
        if created_temp:
            # Preserve the staging directory for further inspection.
            pass

    return 0


def prepare_staging_dir(staging_dir: Path | None) -> tuple[Path, bool]:
    if staging_dir is not None:
        staging_dir = staging_dir.resolve()
        staging_dir.mkdir(parents=True, exist_ok=True)
        if any(staging_dir.iterdir()):
            raise RuntimeError(f"Staging directory {staging_dir} is not empty.")
        return staging_dir, False

    temp_dir = Path(tempfile.mkdtemp(prefix="codex-npm-stage-"))
    return temp_dir, True


def stage_sources(staging_dir: Path, version: str, package: str) -> None:
    if package == "llmx":
        bin_dir = staging_dir / "bin"
        bin_dir.mkdir(parents=True, exist_ok=True)
        shutil.copy2(CODEX_CLI_ROOT / "bin" / "llmx.js", bin_dir / "llmx.js")
        rg_manifest = CODEX_CLI_ROOT / "bin" / "rg"
        if rg_manifest.exists():
            shutil.copy2(rg_manifest, bin_dir / "rg")

        readme_src = REPO_ROOT / "README.md"
        if readme_src.exists():
            shutil.copy2(readme_src, staging_dir / "README.md")

        package_json_path = CODEX_CLI_ROOT / "package.json"
    elif package == "llmx-responses-api-proxy":
        bin_dir = staging_dir / "bin"
        bin_dir.mkdir(parents=True, exist_ok=True)
        launcher_src = RESPONSES_API_PROXY_NPM_ROOT / "bin" / "llmx-responses-api-proxy.js"
        shutil.copy2(launcher_src, bin_dir / "llmx-responses-api-proxy.js")

        readme_src = RESPONSES_API_PROXY_NPM_ROOT / "README.md"
        if readme_src.exists():
            shutil.copy2(readme_src, staging_dir / "README.md")

        package_json_path = RESPONSES_API_PROXY_NPM_ROOT / "package.json"
    elif package == "llmx-sdk":
        package_json_path = CODEX_SDK_ROOT / "package.json"
        stage_codex_sdk_sources(staging_dir)
    else:
        raise RuntimeError(f"Unknown package '{package}'.")

    with open(package_json_path, "r", encoding="utf-8") as fh:
        package_json = json.load(fh)
    package_json["version"] = version

    if package == "llmx-sdk":
        scripts = package_json.get("scripts")
        if isinstance(scripts, dict):
            scripts.pop("prepare", None)

        files = package_json.get("files")
        if isinstance(files, list):
            if "vendor" not in files:
                files.append("vendor")
        else:
            package_json["files"] = ["dist", "vendor"]

    with open(staging_dir / "package.json", "w", encoding="utf-8") as out:
        json.dump(package_json, out, indent=2)
        out.write("\n")


def run_command(cmd: list[str], cwd: Path | None = None) -> None:
    print("+", " ".join(cmd))
    subprocess.run(cmd, cwd=cwd, check=True)


def stage_codex_sdk_sources(staging_dir: Path) -> None:
    package_root = CODEX_SDK_ROOT

    run_command(["pnpm", "install", "--frozen-lockfile"], cwd=package_root)
    run_command(["pnpm", "run", "build"], cwd=package_root)

    dist_src = package_root / "dist"
    if not dist_src.exists():
        raise RuntimeError("codex-sdk build did not produce a dist directory.")

    shutil.copytree(dist_src, staging_dir / "dist")

    readme_src = package_root / "README.md"
    if readme_src.exists():
        shutil.copy2(readme_src, staging_dir / "README.md")

    license_src = REPO_ROOT / "LICENSE"
    if license_src.exists():
        shutil.copy2(license_src, staging_dir / "LICENSE")


def copy_native_binaries(vendor_src: Path, staging_dir: Path, components: list[str]) -> None:
    vendor_src = vendor_src.resolve()
    if not vendor_src.exists():
        raise RuntimeError(f"Vendor source directory not found: {vendor_src}")

    components_set = {component for component in components if component in COMPONENT_DEST_DIR}
    if not components_set:
        return

    vendor_dest = staging_dir / "vendor"
    if vendor_dest.exists():
        shutil.rmtree(vendor_dest)
    vendor_dest.mkdir(parents=True, exist_ok=True)

    for target_dir in vendor_src.iterdir():
        if not target_dir.is_dir():
            continue

        dest_target_dir = vendor_dest / target_dir.name
        dest_target_dir.mkdir(parents=True, exist_ok=True)

        for component in components_set:
            dest_dir_name = COMPONENT_DEST_DIR.get(component)
            if dest_dir_name is None:
                continue

            src_component_dir = target_dir / dest_dir_name
            if not src_component_dir.exists():
                print(
                    f"⚠️  Skipping {target_dir.name}/{dest_dir_name}: component not found (build may have failed)"
                )
                continue

            dest_component_dir = dest_target_dir / dest_dir_name
            if dest_component_dir.exists():
                shutil.rmtree(dest_component_dir)
            shutil.copytree(src_component_dir, dest_component_dir)


def run_npm_pack(staging_dir: Path, output_path: Path) -> Path:
    output_path = output_path.resolve()
    output_path.parent.mkdir(parents=True, exist_ok=True)

    with tempfile.TemporaryDirectory(prefix="codex-npm-pack-") as pack_dir_str:
        pack_dir = Path(pack_dir_str)
        stdout = subprocess.check_output(
            ["npm", "pack", "--json", "--pack-destination", str(pack_dir)],
            cwd=staging_dir,
            text=True,
        )
        try:
            pack_output = json.loads(stdout)
        except json.JSONDecodeError as exc:
            raise RuntimeError("Failed to parse npm pack output.") from exc

        if not pack_output:
            raise RuntimeError("npm pack did not produce an output tarball.")

        tarball_name = pack_output[0].get("filename") or pack_output[0].get("name")
        if not tarball_name:
            raise RuntimeError("Unable to determine npm pack output filename.")

        tarball_path = pack_dir / tarball_name
        if not tarball_path.exists():
            raise RuntimeError(f"Expected npm pack output not found: {tarball_path}")

        shutil.move(str(tarball_path), output_path)

    return output_path


if __name__ == "__main__":
    import sys

    sys.exit(main())