The system has drifted. The research_engine bypassed the verification gate and dumped 103 unverified strategies into paper trading. Beyond that fix, this plan addresses: a contract layer to prevent recurrence, simplicity protection so SMA-4-style strategies stay simple, full re-codification of source-derived strategies under the modern engine (multi-TF, 33 indicators, empirical PM, path-dependent costs), pipeline visibility, and an objective-drift monitor.
For each task, tap YES to approve, NO to skip, or MODIFY and write what you actually want. Decisions auto-save. Hit Submit at the bottom when done.
The version bump that justifies a graveyard re-trial:
| Component | v1 (April harness) | v2 (today) |
|---|---|---|
| Timeframe stack | Single TF | Multi-TF mandatory · explicit roles per TF |
| Indicator set | ~8 indicators | 33 indicators · cross-TF interactions |
| Gate layer | Mostly absent | 8 categories · first-class predicates |
| Position mgmt | Hardcoded constants | Empirical per (strategy, instrument) |
| Cost model | Flat fee + slippage | Path-dependent · funding accrued per interval |
| Regime | After-the-fact label | Vector · first-class gate input · bucketed reporting |
5 of 6 components are major version bumps. This is the trigger event for a one-time graveyard re-trial.
signal_locked: true strategies have their signal envelope frozen forever — protected from automatic "improvement."Once submitted, Claude reads your responses and starts executing. You can still come back and edit, but rerunning the build manually after edits is on you.