feat(learn): retrieval and the evaluation boundary (decision-engine 6.3)

learn/retrieve.py: stage 1 is a per-instrument Gower distance over the
profile's allow-listed features with explicit missing (both ran: mean
feature distance; differing states 1; same non-ran state 0; null in one 1;
priors dropped with priors=off), n1 = 40 with seeded tie-breaks; stage 2
re-ranks by r = lam(1 - D) + (1 - lam)cos, signals_only without the
target's vector; the balance rule takes k_ret = 6 (<= k/2 per label, <= 2
per group, <= 2 other families; `short` recorded). eligible() is the only
way into a prompt: not the target's group, not an evaluated group, not the
held-out source or framework, and outside deployment not a near-duplicate
(cos >= 0.98). assert_boundary repeats the check on rendered ids;
demonstrations of a held-out framework swap to their alternates;
deployment_fold excludes a scanned repository that is a corpus group;
seed_memory never hands a case its own group.

learn/folds.py: compile split (25% of groups per primary family, 60/40
boot/val), outer grouped 5-fold stratified by family and label mix,
leave-one-source-out, leave-one-framework-out (insufficient data below 10
groups), assert_disjoint and a folds digest; all seeded.

Tests: test_learn_retrieve.py (hand-computed Gower, lam 0/0.5, balance,
near-duplicates, test_boundary over outer/LOSO/LOFO folds with
demonstrations), test_learn_folds.py.

Co-Authored-By: Claude Opus 5.5 <[email protected]>
Claude-Session: https://claude.ai/code/session_01EmM1j46qgKMh3zqD1QMwEo

.kiro/specs/learned-decision-engine/tasks.md

@@ -52,7 +52,7 @@ a model or embedding call.
       `ousast learn memory embed`; scripted-client tests.
     - **(budget go-ahead)** embedding the store: ~5.0 M tokens, ~$0.10, ceiling $1 (OpenRouter account).
     - _Requirements: 3.2_
-  - [ ] 6.3 Retrieval and the evaluation boundary (no model)
+  - [x] 6.3 Retrieval and the evaluation boundary (no model)
     - `learn/retrieve.py`: per-instrument Gower distance with explicit missing, `n1 = 40`, embedding re-rank
       `r = lam(1 - D) + (1 - lam)cos`, `signals_only` mode, balance rule (`k_ret = 6`), `eligible(example, target,
       fold)`, near-duplicate drop in evaluation, deployment self-exclusion.