#!/bin/bash
set -e

echo "=== Downloading model ==="
MODEL_PATH=$(python3 -c "
from huggingface_hub import hf_hub_download
path = hf_hub_download(
    repo_id='Jackrong/Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled-v2-GGUF',
    filename='Qwen3.5-9B.Q4_K_M.gguf',
)
print(path)
")

echo "Model path: $MODEL_PATH"

echo "=== Starting llama-server ==="
llama-server \
    --model "$MODEL_PATH" \
    --host 127.0.0.1 \
    --port 8080 \
    --ctx-size 2048 \
    --threads 2 \
    --batch-size 256 \
    --log-disable &

# Wait for server to be ready
echo "Waiting for llama-server to start..."
for i in $(seq 1 30); do
    if curl -s http://127.0.0.1:8080/health > /dev/null 2>&1; then
        echo "llama-server is ready!"
        break
    fi
    echo "  attempt $i/30..."
    sleep 2
done

echo "=== Starting Gradio app ==="
exec python3 app.py