"""CLI des PV RAG Agent.

  python -m agent.cli ingest [--no-embed]   Index (neu) aufbauen
  python -m agent.cli ask "Frage?" [--top-k N] [--json]
  python -m agent.cli eval [--answers] [--limit N] [--k 8] [--json-out FILE]
  python -m agent.cli serve [--host 0.0.0.0]
"""
from __future__ import annotations

import argparse
import json
import sys

from .config import Config


def _cmd_ingest(args: argparse.Namespace, cfg: Config) -> int:
    import dataclasses

    from .ingest import build_index
    client = None
    if args.no_embed:
        cfg = dataclasses.replace(cfg, embed_off=True)
    elif not cfg.embed_off:
        from .ollama_client import OllamaClient
        client = OllamaClient(
            cfg.ollama_url,
            embed_timeout_s=cfg.embed_timeout_s,
            chat_timeout_s=cfg.chat_timeout_s,
        )
        if not client.is_up():
            print(
                f"[warn] Ollama unter {cfg.ollama_url} nicht erreichbar — "
                "Index wird BM25-only aufgebaut.",
                file=sys.stderr,
            )
    try:
        stats = build_index(cfg, client=client)
    finally:
        if client is not None:
            client.close()
    print(json.dumps(stats.as_dict(), indent=2, ensure_ascii=False))
    if stats.embed_error:
        print(f"[warn] {stats.embed_error}", file=sys.stderr)
    return 0


def _cmd_ask(args: argparse.Namespace, cfg: Config) -> int:
    from .generate import answer_question
    try:
        result = answer_question(args.question, cfg, top_k=args.top_k)
    except Exception as e:
        print(
            f"[Fehler] Antwortgenerierung fehlgeschlagen: "
            f"{type(e).__name__}: {e}\n"
            f"Ollama erreichbar unter {cfg.ollama_url}? 'curl {cfg.ollama_url}/api/tags'",
            file=sys.stderr,
        )
        return 2
    if args.json:
        print(json.dumps(result, indent=2, ensure_ascii=False))
        return 0
    print(result["answer"])
    if result["sources"]:
        print("\nQuellen:")
        for s in result["sources"]:
            print(f"  - {s['id']} — {s['title']} ({s['stand']})")
    status = "VERWEIGERT" if result["refused"] else (
        "OK" if result["verified"] else "UNVERIFIZIERT"
    )
    print(
        f"\n[{status} · {result['model']} · {result['latency_ms']} ms · "
        f"{result['n_context']} Kontextblöcke]"
    )
    return 0


def _cmd_eval(args: argparse.Namespace, cfg: Config) -> int:
    from .eval.evaluate import run_eval
    return run_eval(cfg, args)


def _cmd_serve(args: argparse.Namespace, cfg: Config) -> int:
    import uvicorn
    uvicorn.run("agent.api:app", host=args.host, port=cfg.port, log_level="info")
    return 0


def main(argv: list[str] | None = None) -> int:
    cfg = Config.from_env()
    parser = argparse.ArgumentParser(prog="agent.cli", description=__doc__)
    sub = parser.add_subparsers(dest="cmd", required=True)

    p_ingest = sub.add_parser("ingest", help="Index (neu) aufbauen")
    p_ingest.add_argument("--no-embed", action="store_true",
                          help="Keine Embeddings erzeugen (BM25-only)")

    p_ask = sub.add_parser("ask", help="Frage stellen")
    p_ask.add_argument("question")
    p_ask.add_argument("--top-k", type=int, default=None)
    p_ask.add_argument("--json", action="store_true")

    p_eval = sub.add_parser("eval", help="Goldset-Evaluation")
    p_eval.add_argument("--answers", action="store_true",
                        help="inkl. Antwortgenerierung (benötigt Ollama)")
    p_eval.add_argument("--limit", type=int, default=None)
    p_eval.add_argument("--k", type=int, default=8, help="K für Recall@k")
    p_eval.add_argument("--json-out", default=None)

    p_serve = sub.add_parser("serve", help="HTTP-API starten")
    p_serve.add_argument("--host", default="127.0.0.1")

    args = parser.parse_args(argv)
    handlers = {
        "ingest": _cmd_ingest,
        "ask": _cmd_ask,
        "eval": _cmd_eval,
        "serve": _cmd_serve,
    }
    return handlers[args.cmd](args, cfg)


if __name__ == "__main__":
    raise SystemExit(main())