BuyingAgent/backend/scripts/bootstrap.py

from __future__ import annotations

import json
from datetime import datetime, timezone
from pathlib import Path

from sqlalchemy.orm import Session

from app.domain.validation import parse_scoring_model
from app.persistence.db import SessionLocal
from app.persistence.models import ScoringModelRecord, SourceRecord
from app.services.catalog_service import ensure_product_category, ensure_source_category

ROOT = Path(__file__).resolve().parent.parent
RULES = ROOT / "rules" / "generic-v1.json"


def run_bootstrap(session: Session) -> None:
    _seed_source(session)
    _seed_scoring_model(session)
    ensure_product_category(session, "notebook", "Notebooks")
    ensure_source_category(
        session,
        source_id="geizhals",
        external_category_key="nb",
        product_category_id="notebook",
        name="Notebooks",
        source_url="https://geizhals.de/?cat=nb",
    )
    session.commit()


def _seed_source(session: Session) -> None:
    _upsert_source(session, "manual", "Manual entry", "manual")
    _upsert_source(session, "geizhals", "Geizhals", "geizhals")


def _upsert_source(session: Session, source_id: str, name: str, adapter_type: str) -> None:
    existing = session.get(SourceRecord, source_id)
    if existing is None:
        session.add(SourceRecord(id=source_id, name=name, adapter_type=adapter_type))
        return
    if existing.adapter_type != adapter_type:
        raise SystemExit(f"bootstrap conflict: source '{source_id}' has a different adapter_type")


def _seed_scoring_model(session: Session) -> None:
    definition = json.loads(RULES.read_text(encoding="utf-8"))
    model = parse_scoring_model(definition)
    existing = session.get(ScoringModelRecord, model.version)
    if existing is None:
        session.add(
            ScoringModelRecord(
                version=model.version,
                algorithm_id=model.algorithm_id,
                definition=model.definition,
                definition_hash=model.definition_hash,
                created_at=datetime.now(timezone.utc),
            )
        )
        return
    if existing.definition_hash != model.definition_hash:
        raise SystemExit(
            f"bootstrap conflict: scoring model {model.version} hash "
            f"{existing.definition_hash} != {model.definition_hash}"
        )


def main() -> None:
    session = SessionLocal()
    try:
        run_bootstrap(session)
        print("bootstrap ok")
    finally:
        session.close()


if __name__ == "__main__":
    main()