self-study-agent: self-driving loop, no memory format details, auto_repeat config

- Replace static pipeline diagram with self-driving loop (check memory → decide → execute → repeat)
- Remove detailed memory structure JSON schemas from all files
- Remove honcho-specific storage strategy from skill (storage is caller's responsibility)
- Add auto_repeat section to config.yaml (enabled, max_sessions_per_chat, stop_conditions)
- Add rule 8 (auto-repeat) and rule 9 (termination conditions) to execution rules
- Add session transition logic to adaptation.md (due cards → review, incomplete → study)

skills/self-study-agent/feedback/interleaving.md

@@ -69,27 +69,4 @@ interleaving:
 - 현재 주제 정답률 50%↓ → 이전 주제 비중 0.2로 감소
 - 특정 이전 주제 오답률 높음 → 해당 주제 비중 증가
 
-## 메모리 저장 형식
-
-```json
-{
-  "session_topics": [
-    {
-      "topic_id": "rust_async",
-      "source_session": 1,
-      "question_count": 7,
-      "correct_count": 6
-    },
-    {
-      "topic_id": "tokio_internals",
-      "source_session": 2,
-      "question_count": 3,
-      "correct_count": 2
-    }
-  ],
-  "interleaving_stats": {
-    "mix_ratio": 0.3,
-    "cross_session_accuracy": 0.83
-  }
-}
-```
+교차 학습 세션 구성을 메모리에 저장합니다.