okx-strategy-research

OKX Strategy Research

Strategies are Python modules that define on_bar(ctx). The host owns the clock, the market window, matching, sizing, and risk. A strategy returns one decision per bar and never receives an exchange client, credentials, or an order API.

Read references/python-api.md before writing code. Use the documented field names directly; do not probe for spellings.

Workflow

1. Confirm the environment once with strategy_environment. If it is not ready, tell the user to run desic-okx strategy env --setup rather than attempting installation yourself.
2. Write the strategy. Return exactly one decision per bar. Do not pass a contract count — the host derives size from its own budget.
3. Call strategy_validate_source before every backtest. It returns violations with line numbers in milliseconds, so it is always cheaper than discovering a forbidden import after queuing.
4. Check coverage with data_coverage for the instrument and range you intend to test. Repair gaps with data_download first: a backtest over a window with a hole fails closed rather than skipping the minute.
5. Queue the run with strategy_run_backtest. Give meaningful experiments an experimentName and notes; these are editable research metadata and never change source identity, assumptions, or results. It returns a runId immediately. Poll strategy_get_run until status is completed, failed, or cancelled. Never assume a run finished because the call returned.
6. Read details only as needed, through strategy_get_run_equity, strategy_get_run_trades, and strategy_get_run_actions. Request pages; a full equity curve is tens of thousands of points.
7. To tune parameters, use strategy_run_optimize rather than running backtests in a loop and picking the best. It splits the window and ranks on a segment the candidates never saw; choosing by hand across whole-window results selects for overfitting with no way to detect it. Read references/tools-and-data.md before reporting a search.
8. When testing several strategies as one allocation, use strategy_run_portfolio_backtest. It reserves fixed capital sleeves on one shared initial account and recomputes the aggregate equity and drawdown. It does not simulate margin borrowing or netting between strategies; do not describe it as dynamic cross-margin portfolio execution.
9. To weigh two runs against each other, use strategy_compare_runs rather than quoting two reports in sequence. Read its warnings first and repeat them: two runs over different data, instruments, windows, or costs are not two answers to one question, and that is invisible in the metrics alone.
10. When the user asks for a detailed report, visual report, HTML report, charts, or to open/view a report (including Chinese requests such as "详细报告", "HTML 报告", "打开报告", or "查看图表"), generate it immediately with strategy_open_report or strategy_open_comparison. Do not replace that action with paged data reads or merely tell the user which CLI command they could run.