#!/bin/bash
# swap-gpu-dense-model.sh — Swap RTX 3090 from qwen3.6-27B-code to SmartCode-Fable-5
# Run when download completes: ssh root@192.168.68.8 'bash -s' < this script
#
# Usage: bash swap-gpu-dense-model.sh
# Requires: new model at /home/llmuser/models/SmartCode-Fable-5-27B-UD-Q4_K_XL.gguf

set -e

MODEL_PATH="/home/llmuser/models/SmartCode-Fable-5-27B-UD-Q4_K_XL.gguf"
OLD_WRAPPER="/home/llmuser/llama-wrapper.sh"

echo "═══ Swapping gpu-dense to SmartCode-Fable-5 ═══"

# 1. Verify model file
if [ ! -f "$MODEL_PATH" ]; then
    echo "❌ Model not found at $MODEL_PATH"
    echo "   Download: curl -L -o $MODEL_PATH <huggingface-url>"
    exit 1
fi

MODEL_SIZE=$(ls -lh "$MODEL_PATH" | awk '{print $5}')
echo "✅ Model found: $MODEL_SIZE"

# 2. Create new wrapper script for SmartCode-Fable-5
cat > /home/llmuser/llama-fable-wrapper.sh << 'WRAPPER'
#!/bin/bash
# SmartCode-Fable-5 llama-server wrapper for RTX 3090
# Sampler settings from model card: temp 0.9, top-p 0.95, top-k 60, repeat-penalty off

PORT=8080
GHOST_PID=$(ss -tlnp 2>/dev/null | grep -Po ":${PORT}\s+.*pid=\K[0-9]+" | head -1)
if [ -n "$GHOST_PID" ] && [ "$GHOST_PID" != "$$" ]; then
    echo "[wrapper] Port $PORT occupied by ghost pid $GHOST_PID — cleaning up" >&2
    kill -9 "$GHOST_PID" 2>/dev/null
    sleep 2
fi

exec /usr/local/bin/llama-server \
    --model /home/llmuser/models/SmartCode-Fable-5-27B-UD-Q4_K_XL.gguf \
    --ctx-size 131072 \
    --cache-type-k q4_0 \
    --cache-type-v q4_0 \
    --flash-attn 1 \
    --cont-batching \
    --parallel 1 \
    --batch-size 2048 \
    --ubatch-size 1024 \
    --n-gpu-layers 99 \
    --temp 0.9 \
    --top-p 0.95 \
    --top-k 60 \
    --min-p 0.0 \
    --repeat-penalty 1.0 \
    --api-key not-needed \
    --port 8080 \
    --host 0.0.0.0
WRAPPER

chmod 755 /home/llmuser/llama-fable-wrapper.sh
echo "✅ Created /home/llmuser/llama-fable-wrapper.sh"

# 3. Update systemd service to use new wrapper
echo "📝 Updating systemd service..."
sed -i 's|ExecStart=/home/llmuser/llama-wrapper.sh|ExecStart=/home/llmuser/llama-fable-wrapper.sh|' /etc/systemd/system/llama-server.service
systemctl daemon-reload

# 4. Stop old server, start new
echo "🔄 Restarting llama-server..."
systemctl stop llama-server
sleep 3
systemctl start llama-server
sleep 8

# 5. Verify
echo ""
echo "═══ Verification ═══"
systemctl is-active llama-server
echo ""
echo "Port 8080:"
ss -tlnp 2>/dev/null | grep ":8080" | head -1
echo ""
echo "GPU VRAM:"
nvidia-smi --query-gpu=memory.used,memory.total,utilization.gpu --format=csv,noheader 2>/dev/null
echo ""
echo "=== Health check ==="
curl -s --max-time 5 http://localhost:8080/health 2>/dev/null
echo ""
echo ""
echo "✅ Swap complete. Test via LiteLLM:"
echo "  curl -s http://192.168.68.116/v1/chat/completions -H 'Authorization: Bearer <key>' -H 'Content-Type: application/json' -d '{\"model\":\"gpu-dense\",\"messages\":[{\"role\":\"user\",\"content\":\"write hello world in python\"}],\"max_tokens\":100}'"