plan(ml-alpha): three-plan rollout for CfC+PPO greenfield
Plan 1 (Phase A, ~3000 lines): ml-alpha library scaffold, ISV bus,
mapped-pinned slots, CUDA build.rs, six perception kernels with
bit-equiv tests, AdamW + BCE, Graph A capture, Phase A trainer +
binary, CfC-vs-Mamba2 gate. Bite-sized 5-step TDD across 18 tasks.
Plan 2 (Phase B, ~780 lines): build_state, policy_forward (CfC
actor+critic), sample_action, replay buffer, multi-env rollout, GAE,
advantage_normalize, fused PPO loss, EWC, Graphs B+C, seven ISV
controllers, kill-switch, atomic weights swap, walk-forward CV across
6 folds. 19 tasks; tasks 2+ use compressed Step 2-5 TDD cycle pending
re-detail at the Plan 1 gate boundary.
Plan 3 (live, ~560 lines): IBKR adapter audit, AlphaPpoStrategy in
trading_agent_service, cold-start 4-state FSM, disconnect/failure
handling, observability, alpha-control IPC + fxt CLI, restart
semantics, paper trading harness (5 days), $1k live deploy with
manual ack gate, 5-day live window. 10 tasks.
Each plan has gate-pass criteria gating the next. On failure: post-
mortem + spec delta, no advance.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
056b4abe52