Loading…
Build plan · ATLAS · Review & decide

ATLAS — pipeline realignment + sophistication codification.

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.

System ATLAS DB postgres :5434/atlas Engine v1 → v2 re-trial Scope 7 phases · 36 tasks
0
Yes
0
No
0
Modify
36
Pending
0 of 36 reviewed

Reference — Engine v1 → v2 component delta

The version bump that justifies a graveyard re-trial:

Componentv1 (April harness)v2 (today)
Timeframe stackSingle TFMulti-TF mandatory · explicit roles per TF
Indicator set~8 indicators33 indicators · cross-TF interactions
Gate layerMostly absent8 categories · first-class predicates
Position mgmtHardcoded constantsEmpirical per (strategy, instrument)
Cost modelFlat fee + slippagePath-dependent · funding accrued per interval
RegimeAfter-the-fact labelVector · 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.

Reference — Codification fidelity rule

0% reviewed

Submit final decisions?

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.