# AI Data Analyst - Setup Instructions
#
# Single source of truth for local environment setup.
# Webapp reads this, substitutes placeholders, and generates clipboard text.
#
# Placeholders (filled from instance.yaml by webapp):
#   {server_host}  - server IP or hostname
#   {ssh_alias}    - SSH config alias (instance.yaml: server.ssh_alias)
#   {ssh_key}      - SSH private key path (instance.yaml: server.ssh_key)
#   {username}     - analyst username on server
#   {webapp_url}   - webapp URL
#   {project_dir}  - local project folder name (instance.yaml: server.project_dir)

header: |
  Set up my AI Data Analyst local environment.

connection:
  server_host: "{server_host}"
  webapp_url: "{webapp_url}"
  username: "{username}"
  ssh_key: "{ssh_key}"

steps:
  - name: "SSH config"
    description: |
      Check ~/.ssh/config - if a Host entry named "{ssh_alias}" already exists
      with a DIFFERENT server, ask me what name to use instead.
      Otherwise add:
        Host {ssh_alias}
          HostName {server_host}
          User {username}
          IdentityFile {ssh_key}
          StrictHostKeyChecking accept-new
      Then test: ssh {ssh_alias} echo ok

  - name: "Create project folders"
    commands:
      - "mkdir -p server/docs server/scripts server/parquet server/metadata server/examples"
      - "mkdir -p user/duckdb user/notifications user/artifacts user/scripts user/parquet user/sessions"
      - 'printf "ssh_alias={ssh_alias}\nserver_host={server_host}\nwebapp_url={webapp_url}\n" > .sync_connection'

  - name: "Download from server"
    description: |
      Use rsync with --no-perms --no-group to avoid macOS permission errors.
      Skip directories that don't exist on the server (rsync exit code 23 = missing source).
    commands:
      - "rsync -avz --no-perms --no-group {ssh_alias}:server/scripts/ ./server/scripts/"
      - "rsync -avz --no-perms --no-group {ssh_alias}:server/docs/ ./server/docs/"
      - "rsync -avz --no-perms --no-group {ssh_alias}:server/examples/ ./server/examples/"
      - "rsync -avz --no-perms --no-group {ssh_alias}:server/metadata/ ./server/metadata/"
      - "rsync -avz --no-perms --no-group --progress {ssh_alias}:server/parquet/ ./server/parquet/"
    note: "Some folders may be empty if data sync hasn't run on the server yet. That's OK."

  - name: "Set up Python venv"
    commands:
      - "python3 -m venv .venv"
      - "source .venv/bin/activate"
      - "pip install pandas pyarrow duckdb pyyaml python-dotenv"

  - name: "Initialize DuckDB"
    condition: "only if server/scripts/setup_views.sh exists"
    commands:
      - "bash server/scripts/setup_views.sh"

  - name: "Create CLAUDE.md"
    condition: "if server/docs/setup/claude_md_template.txt exists"
    description: |
      Copy the template and replace these placeholders:
        {username} -> {username}
        {ssh_alias} -> {ssh_alias}
        {server_host} -> {server_host}
        {webapp_url} -> {webapp_url}
      Also create CLAUDE.local.md for personal notes (never overwritten by sync).
      Also copy server/docs/setup/claude_settings.json to .claude/settings.json.

existing_project:
  check: "If CLAUDE.md already exists and contains 'AI Data Analyst'"
  message: |
    This directory is already set up. Just sync latest data:
      bash server/scripts/sync_data.sh