"""Preflight checks for OpenAI-compatible LLM endpoints (GenSearcher + browse)."""
from __future__ import annotations

import os
from typing import Tuple

import requests


def normalize_openai_v1_base(url: str) -> str:
    u = (url or "").strip().rstrip("/")
    if not u:
        return ""
    if not u.endswith("/v1"):
        u = u + "/v1"
    return u


def check_v1_models(base_url_v1: str, api_key: str, timeout: float = 15.0) -> Tuple[bool, str]:
    """
    GET {base}/models — standard OpenAI-compatible discovery (vLLM, etc.).
    """
    if not base_url_v1:
        return False, "URL is empty"
    url = base_url_v1.rstrip("/") + "/models"
    headers = {"Authorization": f"Bearer {api_key or 'EMPTY'}"}
    try:
        r = requests.get(url, headers=headers, timeout=timeout)
        if r.status_code == 200:
            return True, "OK"
        return False, f"HTTP {r.status_code}: {r.text[:300]}"
    except requests.exceptions.ConnectionError as e:
        return False, f"Connection failed (nothing listening or blocked): {e}"
    except requests.exceptions.Timeout:
        return False, "Timeout — server not responding"
    except requests.exceptions.RequestException as e:
        return False, str(e)


def is_localhost_url(url: str) -> bool:
    u = (url or "").lower()
    return "127.0.0.1" in u or "localhost" in u


def llm_endpoint_status() -> str:
    """Human-readable markdown for Gradio banner."""
    gen_base = normalize_openai_v1_base(os.environ.get("OPENAI_BASE_URL", ""))
    gen_key = os.environ.get("OPENAI_API_KEY", "EMPTY")
    browse_base = normalize_openai_v1_base(os.environ.get("BROWSE_SUMMARY_BASE_URL", ""))
    browse_key = os.environ.get("BROWSE_SUMMARY_API_KEY", os.environ.get("OPENAI_API_KEY", "EMPTY"))

    lines = ["### Endpoint checks", ""]

    if not gen_base:
        lines.append(
            "**GenSearcher LLM:** `OPENAI_BASE_URL` is **not set**.\n\n"
            "- **All compute in this Space (recommended for your case):** add a Space variable "
            "`START_VLLM_GENSEARCHER=1` (and enough GPU). The entrypoint starts **vLLM for Gen-Searcher-8B inside this "
            "same container** and sets `OPENAI_BASE_URL` to `http://127.0.0.1:8002/v1`. That is still **this Space** — "
            "not a second Hugging Face Space. The app talks to vLLM over **localhost** inside the container (normal for vLLM).\n\n"
            "- **Or** set `OPENAI_BASE_URL` yourself to any OpenAI-compatible **`…/v1`** URL (only if the model runs elsewhere).\n"
        )
    else:
        ok, msg = check_v1_models(gen_base, gen_key)
        if ok:
            lines.append(f"**GenSearcher LLM** (`OPENAI_BASE_URL`): reachable — `{gen_base}`")
        else:
            lines.append(
                f"**GenSearcher LLM** (`OPENAI_BASE_URL`): **unreachable** — `{gen_base}`\n\n"
                f"- Detail: `{msg}`\n"
            )
            if is_localhost_url(gen_base):
                lines.append(
                    "- You are using **localhost / 127.0.0.1**. Inside a Hugging Face Space, that is **this container only**. "
                    "Either set `START_VLLM_GENSEARCHER=1` (and enough GPU) to run vLLM here, "
                    "or set `OPENAI_BASE_URL` to a **public** inference URL (your vLLM, TGI, etc.).\n"
                )

    lines.append("")
    if os.environ.get("BROWSE_GENERATE_ENGINE", "").strip().lower() == "vllm":
        if not browse_base:
            lines.append(
                "**Browse summarizer:** `BROWSE_SUMMARY_BASE_URL` is **not set** (needed when `BROWSE_GENERATE_ENGINE=vllm`)."
            )
        else:
            ok_b, msg_b = check_v1_models(browse_base, browse_key)
            if ok_b:
                lines.append(f"**Browse LLM:** OK — `{browse_base}`")
            else:
                lines.append(
                    f"**Browse LLM:** **unreachable** — `{browse_base}` — `{msg_b}`"
                )
                if is_localhost_url(browse_base):
                    lines.append(
                        "- Same **localhost** note: use an external Qwen3-VL server or `START_VLLM_BROWSE=1` with extra GPU.\n"
                    )

    return "\n".join(lines)