#!/usr/bin/env bash
set -euo pipefail

NAMESPACE="${NAMESPACE:-awoooi-prod}"
DEPLOYMENT="${DEPLOYMENT:-awoooi-api}"
MODEL="${MODEL:-gemma3:4b}"
TIMEOUT_SECONDS="${TIMEOUT_SECONDS:-60}"

kubectl -n "${NAMESPACE}" exec -i "deploy/${DEPLOYMENT}" -- \
  env CHECK_MODEL="${MODEL}" CHECK_TIMEOUT_SECONDS="${TIMEOUT_SECONDS}" python - <<'PY'
import json
import os
import time
import urllib.error
import urllib.request

model = os.environ["CHECK_MODEL"]
timeout = int(os.environ["CHECK_TIMEOUT_SECONDS"])

endpoints = [
    ("primary", os.environ.get("OLLAMA_URL", "")),
    ("secondary", os.environ.get("OLLAMA_SECONDARY_URL", "")),
    ("fallback", os.environ.get("OLLAMA_FALLBACK_URL", "")),
]

print(f"model={model} timeout={timeout}s")

def request_json(url: str, path: str, payload=None, timeout_seconds=10):
    data = None
    headers = {}
    if payload is not None:
        data = json.dumps(payload).encode()
        headers["Content-Type"] = "application/json"
    req = urllib.request.Request(url.rstrip("/") + path, data=data, headers=headers)
    with urllib.request.urlopen(req, timeout=timeout_seconds) as response:
        return json.loads(response.read().decode())

for label, url in endpoints:
    print(f"\n== {label}: {url or '<missing>'} ==")
    if not url:
        print("status=missing")
        continue

    try:
        tags = request_json(url, "/api/tags", timeout_seconds=10)
        names = sorted(m.get("name", "") for m in tags.get("models", []))
        print("tags=ok", ",".join(names[:12]))
    except Exception as exc:
        print("tags=fail", type(exc).__name__, str(exc)[:160])
        continue

    try:
        ps = request_json(url, "/api/ps", timeout_seconds=10)
        live = ps.get("models", [])
        if not live:
            print("ps=ok live_models=<none>")
        for item in live:
            print(
                "ps=ok",
                f"model={item.get('model')}",
                f"expires={item.get('expires_at')}",
                f"size_vram={item.get('size_vram')}",
                f"context={item.get('context_length')}",
            )
            if item.get("size_vram") == 0:
                print("warning=cpu_only_or_no_vram")
    except Exception as exc:
        print("ps=fail", type(exc).__name__, str(exc)[:160])

    payload = {
        "model": model,
        "prompt": "用繁體中文用一行回答：Ollama health check",
        "stream": False,
        "keep_alive": "8h",
        "options": {"num_predict": 32, "temperature": 0.1},
    }
    start = time.time()
    try:
        result = request_json(url, "/api/generate", payload, timeout_seconds=timeout)
        latency_ms = round((time.time() - start) * 1000)
        response = (result.get("response") or "").replace("\n", " ")[:120]
        print(f"generate=ok latency_ms={latency_ms} response={response}")
    except urllib.error.HTTPError as exc:
        body = exc.read().decode(errors="replace")[:200]
        print("generate=fail", "HTTPError", exc.code, body)
    except Exception as exc:
        print("generate=fail", type(exc).__name__, str(exc)[:200])
PY