#!/usr/bin/env python3
"""Rebuild catalog.json from the public arka-ai.ru OpenAI-compatible models list.

Keep FORCED_MODELS / NON_CHAT in lockstep with opencode/plugins/arka-ai.ts.
"""
from __future__ import annotations

import json
import re
import sys
import urllib.request
from datetime import datetime, timezone
from pathlib import Path

API_URL = "https://api.arka-ai.ru/v1/models"
ROOT = Path(__file__).resolve().parents[1]
OUT = ROOT / "catalog.json"

FORCED_MODELS = [
    "DeepSeek-V4-Pro",
    "deepseek-v4-flash-0731",
    "qwen3.8-max",
    "kimi-k3",
    "MiniMax-M3",
    "GLM-5.3",
]

NON_CHAT = re.compile(
    "|".join(
        [
            "tts",
            "asr",
            "audio",
            "speech",
            "voice",
            "whisper",
            "sensevoice",
            "image",
            r"(^|[.-])img",
            "wan",
            "vidu",
            "video",
            "sora",
            "flux",
            "diffus",
            "kolors",
            "cogview",
            "ocr",
            "embedding",
            r"(^|[.-])embed",
            "rerank",
            "clip",
            "moderation",
            r"(^|[.-])filter",
            "detect",
            "classif",
            r"(^|[.-])location",
            r"(^|[.-])search",
            "comfyui",
            "meme",
            "hello",
            r"(^|[.-])sam",
            "florence",
            "esrgan",
            "rmbg",
            "background",
            "poster",
            r"(^|[.-])face",
            r"(^|[.-])lip",
            "translate",
            r"(^|[.-])mt([2-]|$)",
            r"(^|[.-])bge",
            r"(^|[.-])e5",
            r"(^|[.-])jina",
            r"(^|[.-])mpnet",
            "spark-tts",
            "cosyvoice",
            "chattts",
            "indextts",
            "step-audio",
            "fish-speech",
            "cosy",
            "mate-gguf",
            "tokenizer",
        ]
    ),
    re.I,
)


def fetch_models() -> list[dict]:
    req = urllib.request.Request(API_URL, headers={"User-Agent": "arka-public-catalog-sync"})
    with urllib.request.urlopen(req, timeout=30) as resp:
        payload = json.load(resp)
    data = payload.get("data") or []
    if not isinstance(data, list) or not data:
        raise SystemExit("empty models list from api.arka-ai.ru")
    return data


def keep(item: dict) -> bool:
    mid = item.get("id") or ""
    return mid in FORCED_MODELS or not NON_CHAT.search(mid)


def main() -> int:
    raw = fetch_models()
    chat = [item for item in raw if keep(item)]
    chat.sort(key=lambda item: item.get("id") or "")
    missing = [mid for mid in FORCED_MODELS if not any(item.get("id") == mid for item in chat)]
    if missing:
        print("warning: forced models missing from catalog:", ", ".join(missing), file=sys.stderr)

    out = {
        "updated_at": datetime.now(timezone.utc).strftime("%Y-%m-%dT%H:%M:%SZ"),
        "source": API_URL,
        "raw_count": len(raw),
        "chat_count": len(chat),
        "object": "list",
        "data": [{"id": item.get("id"), "object": "model"} for item in chat],
    }
    text = json.dumps(out, ensure_ascii=False, indent=2) + "\n"
    OUT.write_text(text, encoding="utf-8")
    print(f"wrote {OUT} raw={out['raw_count']} chat={out['chat_count']}")
    return 0


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