#!/usr/bin/env bash
# Validation end-to-end test for vLLM on dankclaw
# Sends a simple prompt and measures total response time
# Usage: ./scripts/validate.sh [host] [port]

HOST="${1:-dankclaw}"
PORT="${2:-8000}"
MODEL="bottlecapai/ThinkingCap-Qwen3.6-27B-FP8"

echo "=== vLLM Validation Test ==="
echo "Target: ${HOST}:${PORT}"
echo "Model: ${MODEL}"
echo ""

START_TIME=$(date +%s%N)

RESPONSE=$(curl -s -w "\n%{http_code}" \
    "http://${HOST}:${PORT}/v1/chat/completions" \
    -H "Content-Type: application/json" \
    -d "{
        \"model\": \"${MODEL}\",
        \"messages\": [
            {\"role\": \"user\", \"content\": \"What is 2 plus 2? Answer in one word.\"}
        ],
        \"max_tokens\": 128,
        \"temperature\": 0.1
    }")

END_TIME=$(date +%s%N)
ELAPSED_MS=$(( (END_TIME - START_TIME) / 1000000 ))

HTTP_CODE=$(echo "$RESPONSE" | tail -1)
BODY=$(echo "$RESPONSE" | sed '$d')

echo "HTTP Status: ${HTTP_CODE}"
echo "Response Time: ${ELAPSED_MS}ms"
echo ""

if [ "$HTTP_CODE" = "200" ]; then
    CONTENT=$(echo "$BODY" | python3 -c "import sys,json; print(json.load(sys.stdin)['choices'][0]['message']['content'].strip())" 2>/dev/null)
    echo "Model Output: ${CONTENT}"
    echo ""
    echo "PASS — Server responded successfully"
    echo "TIME=${ELAPSED_MS}"
    exit 0
else
    echo "FAIL — Server returned HTTP ${HTTP_CODE}"
    echo "Response: ${BODY}"
    exit 1
fi