Lona

Use this when the user has existing Backtrader Python code to upload as a new strategy.

Prefer lona_create_strategy_from_description if the user wants to create a strategy from a description instead of uploading existing code.

Requirements for the code:

• Must import backtrader: import backtrader as bt
• Must define a class inheriting from bt.Strategy
• Parameters use tuple format: params = (('name', value), ...)
• Initialize indicators in __init__, trading logic in next()

Example:

import backtrader as bt

class Strategy(bt.Strategy):
    params = (('period', 20),)

    def __init__(self):
        self.sma = bt.indicators.SMA(period=self.p.period)

    def next(self):
        if self.data.close[0] > self.sma[0]:
            self.buy()

Use this when the user wants to create a new trading strategy from a natural language description. This is the recommended way to create strategies.

The tool will: 1. Analyze the user's description to extract trading requirements 2. Generate properly formatted Backtrader Python code 3. Save the strategy to the user's account 4. Return the strategy ID ready for backtesting with lona_run_backtest

Examples of valid descriptions:

• "A momentum strategy that buys when RSI crosses above 30 and sells below 70"
• "Trend following using 20 and 50 period moving averages with 2% stop loss"
• "Mean reversion with Bollinger Bands - buy at lower band, sell at upper band"
• "BTC trend strategy using EMA crossover with ADX filter and ATR-based stops"

Use this when the user wants to download cryptocurrency data from Binance for backtesting. Automatically downloads, processes, and uploads data to the user's Lona account.

Supported intervals: 1m, 5m, 15m, 30m, 1h, 4h, 1d

Practical limits (Binance REST API):

• 1m data: up to ~6 months
• 5m data: up to ~2 years
• 1h+ data: several years of history

Returns a symbol ID that can be used immediately with lona_run_backtest.

Use this when the user wants comprehensive backtest results including detailed metrics, trade history, and per-symbol performance breakdown. For visual trade analysis, follow up with lona_get_report_chart.

Use this when the user wants to see a backtest report summary. Returns key performance metrics including total return, Sharpe ratio, maximum drawdown, win rate, and number of trades.

Use this when the user wants to visualize a backtest on a chart. Displays an interactive candlestick chart with buy/sell markers showing entry and exit points. Only works for completed reports.

Use this to check the progress of a running backtest. Returns current status (PENDING, EXECUTING, PROCESSING, COMPLETED, or FAILED) and whether the backtest is complete. Call this after lona_run_backtest to monitor progress.

Use this when the user wants details about a specific trading strategy. Requires a strategy ID. Returns the strategy name, description, version, language, and timestamps.

Use this when the user wants to view or analyze the source code of a trading strategy. Requires a strategy ID. Returns the Python Backtrader code that implements the strategy logic.

Use this when the user wants details about a specific market data symbol. Returns the symbol name, description, data type, exchange, asset class, and whether it is a global or user-uploaded dataset.

Use this when the user wants to preview the actual price data for a symbol. Returns OHLCV (Open, High, Low, Close, Volume) time-series data. Useful for verifying data quality before running a backtest.

Use this when the user wants to see their backtest reports or check on running backtests. Returns reports with status, performance metrics (return, Sharpe ratio, trades), and timestamps. Filter by strategy_id or status (PENDING, EXECUTING, PROCESSING, COMPLETED, FAILED).

Use this when the user wants to see their trading strategies or find a specific strategy. Returns a list of strategies with names, IDs, descriptions, and version info. Supports pagination via skip/limit parameters.

Use this when the user wants to see available market data for backtesting. Returns user-uploaded data files by default. Set isGlobal=true to see pre-loaded market data (US equities, crypto, forex). Each symbol has an ID used with lona_run_backtest.

Register this AI agent and provision a short-lived API token.

Use this before any other Lona tools if you do not already have an API token. Works automatically: uses registration secret if configured, otherwise requests an invite code from the gateway.

Use this when the user wants to test a trading strategy on historical data. Requires a strategy_id (from lona_list_strategies) and data_ids (from lona_list_symbols or lona_download_market_data).

The backtest runs asynchronously. Returns a report_id to track progress via lona_get_report_status.

Configurable parameters:

• initial_cash: Starting capital (default: 100000)
• commission: Trading commission as decimal (default: 0.001 = 0.1%)
• leverage: Maximum leverage allowed (default: 1)
• parameters: Override strategy parameters (passed to the strategy's params tuple)

Use this when the user wants to modify an existing trading strategy. Requires the strategy ID. You can update the name, description, or code individually or all at once.