#!/usr/bin/env bash
# Pulls ollama/ollama:latest, starts it once, pulls qwen2.5:0.5b (chat, ~400MB) and all-minilm
# (embeddings, ~45MB) inside the running container, then `docker commit`s the result to a local
# image tag. This is the real Testcontainers-recommended pattern for CI: bake the models into
# an image once, and every subsequent test run starts a container that already has them on
# disk -- no registry pull, no flaky network dependency, no per-run latency for the pull itself.
#
# Run this once before scripts/run-all.sh, or whenever you want to refresh the baked models.
set -euo pipefail

IMAGE_TAG="${1:-ollama-baked-qwen05b-minilm:local}"
CONTAINER_NAME="ollama-bake-$$"

echo "Pulling ollama/ollama:latest..."
docker pull ollama/ollama:latest

echo "Starting a container to pull models into..."
docker run -d --name "$CONTAINER_NAME" ollama/ollama:latest
trap 'docker rm -f "$CONTAINER_NAME" >/dev/null 2>&1 || true' EXIT

echo "Waiting for the Ollama server to accept connections..."
until docker exec "$CONTAINER_NAME" ollama list >/dev/null 2>&1; do
	sleep 1
done

echo "Pulling qwen2.5:0.5b (chat)..."
docker exec "$CONTAINER_NAME" ollama pull qwen2.5:0.5b

echo "Pulling all-minilm (embeddings)..."
docker exec "$CONTAINER_NAME" ollama pull all-minilm

echo "Committing to ${IMAGE_TAG}..."
docker commit "$CONTAINER_NAME" "$IMAGE_TAG"

echo "Done. ${IMAGE_TAG} now has both models baked in -- scripts/run-all.sh will not touch the network."