plan(ml-backtesting): CBSW cold-start aggregator implementation plan

Browse Source

4-task atomic ladder (Q1-Q4) implementing spec 566e8bcb0. Each task
maps to one commit per feedback_no_partial_refactor:

  Q1: Cold-start stopgap (bytecode max-confidence policy upload)
  Q2: CBSW kernel aggregator + Tier 1 revert (atomic)
  Q3: Memory pearl pearl_conviction_bootstrap_for_kelly_aggregation
  Q4: Parallelism spec §3.4 cross-reference

Kernel ABI unchanged across all 4 commits — Q2 modifies only
decision_policy_default's body (decision_policy_program left as a
pluggable bytecode-VM experiment surface). Q2 atomically deletes
the Q1 stopgap field/CLI/YAML/harness branch in the same commit
that lands the kernel fix (feedback_no_legacy_aliases compliance:
grep returns zero hits for use_cold_start_stopgap post-Q2).

Validation gates per spec §9:
  - Q1: cluster smoke n_trades > 100, total_pnl != 0 (diagnosis
    confirmation). If n_trades = 0 still, STOP — downstream bug.
  - Q2: pre-existing 11 CUDA tests still pass; 7 new cbsw_*
    regression tests pass; cluster smoke n_trades > 100; ev/s
    rate ratio Q2/Q1 ≥ 0.95.

Self-review confirms all 11 spec sections covered, no placeholders,
type/signature consistency across tasks.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

...

This commit is contained in:

jgrusewski

2026-05-19 21:53:28 +02:00

parent 566e8bcb0a

commit 2130bee006

1 changed files with 1010 additions and 0 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download Patch File Download Diff File Expand all files Collapse all files

1010

docs/superpowers/plans/2026-05-19-cbsw-cold-start-aggregator.md Normal file

File diff suppressed because it is too large Load Diff