"""
BeanFlows.coffee Infrastructure
Cloudflare R2 + Iceberg + Hetzner compute stack
"""

import pulumi
import pulumi_cloudflare as cloudflare
import pulumi_hcloud as hcloud

# Load configuration
config = pulumi.Config()
cloudflare_account_id = config.require("cloudflare_account_id")
hetzner_location = config.get("hetzner_location") or "nbg1"  # Nuremberg datacenter

# ============================================================
# Cloudflare R2 Storage + Data Catalog (Iceberg)
# ============================================================

# R2 bucket for artifacts (CLI + extract/transform packages)
# Note: Import existing bucket with:
# pulumi import cloudflare:index/r2Bucket:R2Bucket beanflows-artifacts <account_id>/beanflows-artifacts
artifacts_bucket = cloudflare.R2Bucket(
    "beanflows-artifacts",
    account_id=cloudflare_account_id,
    name="beanflows-artifacts",
    location="weur",  # Western Europe
)

# R2 bucket for lakehouse (Iceberg tables)
# Note: Import existing bucket with:
# pulumi import cloudflare:index/r2Bucket:R2Bucket beanflows-data-prod <account_id>/beanflows-data-prod
lakehouse_bucket = cloudflare.R2Bucket(
    "beanflows-data-prod",
    account_id=cloudflare_account_id,
    name="beanflows-data-prod",
    location="weur",
)

# ============================================================
# Hetzner Cloud Infrastructure
# ============================================================

# SSH key for server access
ssh_key = hcloud.SshKey(
    "materia-ssh-key",
    name="materia-deployment-key",
    public_key=config.require_secret("ssh_public_key"),
)

# Small CCX instance for supervisor (runs materia CLI to orchestrate pipelines)
# This is an always-on instance that creates/destroys ephemeral workers on-demand
supervisor_server = hcloud.Server(
    "materia-supervisor",
    name="materia-supervisor",
    server_type="ccx11",  # 2 vCPU, 4GB RAM, ~€4/mo (cheapest option)
    image="ubuntu-24.04",
    location=hetzner_location,
    ssh_keys=[ssh_key.id],
    labels={
        "role": "supervisor",
        "project": "materia",
    },
    user_data="""#!/bin/bash
set -e

# Basic server setup
apt-get update
apt-get install -y python3.13 python3-pip curl unzip

# Install Pulumi ESC CLI
curl -fsSL https://get.pulumi.com/esc/install.sh | sh
export PATH="$HOME/.pulumi/bin:$PATH"
echo 'export PATH="$HOME/.pulumi/bin:$PATH"' >> /root/.bashrc

# Create deployment directory
mkdir -p /opt/materia

# Configure environment
echo 'Setup complete. Materia CLI will be deployed via CI/CD.' > /opt/materia/README.txt
""",
)

# Note: Workers are created on-demand by the materia CLI
# No always-on worker instances in this architecture

# Firewall for servers (restrict to SSH + outbound only)
firewall = hcloud.Firewall(
    "materia-firewall",
    name="materia-firewall",
    rules=[
        # Allow SSH from anywhere (consider restricting to your IP)
        hcloud.FirewallRuleArgs(
            direction="in",
            protocol="tcp",
            port="22",
            source_ips=["0.0.0.0/0", "::/0"],
        ),
        # Allow all outbound traffic
        hcloud.FirewallRuleArgs(
            direction="out",
            protocol="tcp",
            port="any",
            destination_ips=["0.0.0.0/0", "::/0"],
        ),
        hcloud.FirewallRuleArgs(
            direction="out",
            protocol="udp",
            port="any",
            destination_ips=["0.0.0.0/0", "::/0"],
        ),
    ],
)

# Apply firewall to supervisor
supervisor_firewall = hcloud.FirewallAttachment(
    "supervisor-firewall",
    firewall_id=firewall.id,
    server_ids=[supervisor_server.id],
)

# ============================================================
# Outputs
# ============================================================

pulumi.export("artifacts_bucket_name", artifacts_bucket.name)
pulumi.export("lakehouse_bucket_name", lakehouse_bucket.name)
pulumi.export("supervisor_ip", supervisor_server.ipv4_address)

# Export connection info for DuckDB
pulumi.export(
    "duckdb_r2_config",
    pulumi.Output.all(cloudflare_account_id, lakehouse_bucket.name).apply(
        lambda args: {
            "account_id": args[0],
            "bucket": args[1],
            "catalog_uri": f"https://catalog.cloudflarestorage.com/{args[0]}/r2-data-catalog",
        }
    ),
)