strategy-generate

Workflow

1. Requirements parsing: parse user intent, extract instrument codes, time range, and strategy logic, then write config.json
2. Strategy design: think through the 5 questions of data / signal / position sizing / backtest / validation
3. Strategy coding: write code/signal_engine.py (following the SignalEngine contract)
4. Syntax check: bash("python -c \"import ast; ast.parse(open('code/signal_engine.py').read()); print('OK')\"")
5. Run backtest: call the backtest tool (built into the engine; no need to write run_backtest.py)
6. Evaluate results: use the backtest tool's structured metrics, validation and artifact summary. Read artifacts/metrics.csv or targeted rows with read_run_artifact only when the requested evidence is missing from that summary. Judge by the review criteria and report failures honestly.
7. Fix implementation errors: repair code/contract errors and rerun to verify. Poor returns in a correctly implemented strategy are a valid result: report them and stop. Change the strategy or test additional candidates only when the user requested optimization or comparison, within their specified scope. Deeper attribution and robustness research are performed when requested, not added to every backtest.

You only need to write signal_engine.py and config.json. The backtest tool automatically handles data loading and backtest execution.

Adapting a registered strategy

1. Read get_strategy_evidence(strategy_id="sdm:...") for the parent's description and computed regime definitions. A stale, disabled, decayed or inadequately evidenced parent cannot be adapted.
2. Call adapt_strategy(strategy_id=..., name=..., universe=..., config=...) with explicit codes and date window. Only name, universe and optional position sizing may change. Signal definition, entry and exit rules remain the parent's. Missing inputs require a question, never a fabricated metric or threshold.
3. Use the returned assigned run_dir and seeded config.json. Generate the child's code/signal_engine.py from its description using the contract below; never copy a parent run's metrics. Preserve the bound codes, dates and strategy_adaptation metadata. Record model provenance through the normal write tool.
4. Call backtest(run_dir=...), inspect its artifacts, then refresh_strategy_evidence(runs=[{"strategy_id": "sdm:<child>", "run_dir": "<assigned>"}], scope="strategies"). This updates only successful named strategies and preserves the parent's evidence. Refresh refuses a different run or changed config/code/results against the run card.
5. Read the child's evidence and report its actual quality, cost and decay warnings. A successful backtest is not adequate regime evidence or independent approval. An unchanged mathematical signal can legitimately generate identical code for another universe; hashes establish provenance, not semantic correctness of generated Python.