Woods.configure do |config|
  config.output_dir = Rails.root.join('tmp/woods')
  config.max_context_tokens = 8000
  # ...
end

Woods.configure do |config|
  config.output_dir = Rails.root.join('tmp/woods')

  # In CI, only extract models and controllers for faster builds
  config.extractors = %i[models controllers services] if ENV['CI']
end

Woods.configure do |config|
  # Inside Docker, /app is the Rails root
  config.output_dir = ENV.fetch('WOODS_OUTPUT_DIR', Rails.root.join('tmp/woods'))
end

Woods.configure do |config|
  # Use OpenAI in production/CI where the API key is set,
  # fall back to Ollama for local development (free, no API key needed)
  if ENV['OPENAI_API_KEY']
    config.embedding_provider = :openai
    config.embedding_model = 'text-embedding-3-small'
    config.embedding_options = { api_key: ENV['OPENAI_API_KEY'] }
  else
    config.embedding_provider = :ollama
    config.embedding_model = 'nomic-embed-text'
    config.embedding_options = { base_url: ENV.fetch('OLLAMA_URL', 'http://localhost:11434') }
  end
end

config.embedding_provider = :openai
config.embedding_model = 'text-embedding-3-small'
config.embedding_options = {
  api_key: ENV['OPENAI_API_KEY'],
  dimensions: 1536
}

config.embedding_provider = :ollama
config.embedding_model = 'nomic-embed-text'
config.embedding_options = {
  base_url: 'http://localhost:11434'
}

config.vector_store = :pgvector
config.vector_store_options = {
  connection: ActiveRecord::Base.connection,
  dimensions: 1536
}

bundle exec rails generate woods:pgvector
bundle exec rails db:migrate

config.vector_store = :qdrant
config.vector_store_options = {
  url: 'http://localhost:6333',
  collection: 'woods',
  dimensions: 1536
}

config.metadata_store = :sqlite
config.metadata_store_options = {
  database: Rails.root.join('tmp/woods/metadata.sqlite3').to_s
}

# Local development — no external services needed
Woods.configure_with_preset(:local)
# → in_memory vectors, SQLite metadata, in_memory graph, Ollama embeddings

# PostgreSQL — requires pgvector extension and OpenAI API key
Woods.configure_with_preset(:postgresql)
# → pgvector vectors, SQLite metadata, in_memory graph, OpenAI embeddings

# Production — requires Qdrant server and OpenAI API key
Woods.configure_with_preset(:production)
# → Qdrant vectors, SQLite metadata, in_memory graph, OpenAI embeddings

Woods.configure_with_preset(:local) do |config|
  config.max_context_tokens = 16000
  config.embedding_model = 'mxbai-embed-large'
end

config.session_tracer_enabled = true
config.session_store = Woods::SessionTracer::FileStore.new(
  Rails.root.join('tmp/session_traces')
)
config.session_exclude_paths = ['/health', '/metrics', '/assets']

config.add_gem 'devise', paths: ['lib/devise/models'], priority: :high
config.add_gem 'pundit', paths: ['lib/pundit'], priority: :medium
config.add_gem 'sidekiq', paths: ['lib/sidekiq/worker', 'lib/sidekiq/job'], priority: :high

config.extractors = %i[
  models controllers services components view_components
  jobs mailers graphql serializers managers policies validators
  rails_source
]