spec(learned-decision-engine): design and tasks revised for the AI classifier

In-house DSPy-style program (retrieve -> classify(k)) on the metered client;
example store with signal-profile Gower neighbours re-ranked by code embeddings;
balanced Brier metric, bootstrap few-shot and instruction search on a compile
split; Platt calibration on other folds; cached replay; tasks 6.1-6.7 with paid
steps flagged for go-ahead.

Co-Authored-By: Claude Opus 5.5 <[email protected]>
Claude-Session: https://claude.ai/code/session_01EmM1j46qgKMh3zqD1QMwEo
This commit is contained in:
Marius Ciepluch
2026-10-01 09:22:29 +02:00
co-authored by Claude Opus 5.5
parent 2d69a8b677
commit b6a49fa4dc
3 changed files with 679 additions and 316 deletions
@@ -1,9 +1,9 @@
{
"feature_name": "learned-decision-engine",
"created_at": "2026-09-30T14:00:00Z",
"updated_at": "2026-10-01T09:00:00Z",
"updated_at": "2026-10-01T10:00:00Z",
"language": "en",
"phase": "requirements-amended",
"phase": "design-generated",
"approvals": {
"requirements": {
"generated": true,