2nd/10_Wiki/Topic_Programming/AI_and_ML/P-Reinforce.md

id, title, category, status, canonical_id, aliases, duplicate_of, source_trust_level, confidence_score, verification_status, tags, raw_sources, last_reinforced, github_commit, tech_stack

id	title	category	status	canonical_id	aliases	duplicate_of	source_trust_level	confidence_score	verification_status	tags	raw_sources	last_reinforced	github_commit	tech_stack
wiki-2026-0508-p-reinforce	P-Reinforce	10_Wiki/Topics	verified	self	Auto-Reinforce Wiki-Reinforcement Reinforcement-Marker	none	A	0.9	applied	wiki automation knowledge-management claude-code		2026-05-10	pending	language framework markdown obsidian

P-Reinforce

매 한 줄

"매 wiki entry 의 자동 강화 marker". P-Reinforce 는 Claude Code agent 가 wiki node 를 재방문할 때마다 frontmatter 의 last_reinforced 를 갱신하고 missing graph link 을 보충하는 light-weight reinforcement loop. 매 hand-curated knowledge graph 의 staleness 방지.

매 핵심

매 trigger 조건

• agent 가 file 을 Read 하고 substantive change (>= 3 lines) 을 적용한 경우.
• backlink resolver 가 dangling [[X]] 을 발견 후 stub 을 만든 경우.
• weekly cron (/loop 7d /reinforce) 의 sweep.

매 frontmatter 의 강화 field

• last_reinforced — ISO date.
• confidence_score — 0..1, decay 0.02/month, +0.05 per reinforcement.
• verification_status — applied | pending | redirected.
• source_trust_level — A/B/C.

매 응용

1. Wiki staleness audit — last_reinforced < 90d 의 file 을 batch 로 재방문.
2. Confidence-weighted retrieval — RAG 가 high-confidence node 을 prefer.
3. Graph hygiene — orphan / dangling link 을 reinforcement pass 에서 fix.

💻 패턴

Frontmatter reinforcement (Python)

import re, yaml, datetime, pathlib

def reinforce(path: pathlib.Path, bump: float = 0.05):
    text = path.read_text()
    m = re.match(r"^---\n(.*?)\n---\n(.*)$", text, re.DOTALL)
    if not m:
        return False
    fm = yaml.safe_load(m.group(1)) or {}
    fm["last_reinforced"] = datetime.date.today().isoformat()
    fm["confidence_score"] = min(0.99, fm.get("confidence_score", 0.5) + bump)
    fm["verification_status"] = "applied"
    new = "---\n" + yaml.safe_dump(fm, sort_keys=False, allow_unicode=True) + "---\n" + m.group(2)
    path.write_text(new)
    return True

Decay sweep (cron)

from datetime import date, timedelta

def decayed(fm: dict, days: int = 90) -> bool:
    last = date.fromisoformat(fm.get("last_reinforced", "1970-01-01"))
    return (date.today() - last) > timedelta(days=days)

stale = [p for p in pathlib.Path("10_Wiki").rglob("*.md")
         if decayed(load_fm(p))]

Dangling link harvest

import re
LINK = re.compile(r"\[\[([^\]|#]+)")
def dangling(root):
    existing = {p.stem for p in root.rglob("*.md")}
    for md in root.rglob("*.md"):
        for tgt in LINK.findall(md.read_text()):
            if tgt not in existing:
                yield md, tgt

Reinforcement-aware retrieval (BM25 + confidence)

def score(doc, query):
    bm = bm25(doc.text, query)
    conf = doc.frontmatter.get("confidence_score", 0.5)
    age = days_since(doc.frontmatter["last_reinforced"])
    decay = max(0.5, 1 - age / 365)
    return bm * conf * decay

Claude Code hook (settings.json)

{
  "hooks": {
    "Stop": [{
      "command": "python ~/scripts/reinforce_touched.py"
    }]
  }
}

매 결정 기준

상황	Approach
매 active editing	inline reinforcement on Write
매 background hygiene	weekly cron sweep
매 large refactor	manual verification_status: applied bump
매 redirect/duplicate	verification_status: redirected, no decay

기본값: Stop hook + weekly sweep 의 조합.

🔗 Graph

• 부모: Knowledge Graph
• 응용: RAG · Agent-Memory

🤖 LLM 활용

언제: 매 long-lived wiki / second-brain 의 staleness 가 문제일 때. 언제 X: 매 ephemeral note / scratchpad — overhead > benefit.

❌ 안티패턴

• Reinforce without read: blind date bump — confidence 의 의미를 잃음.
• Unbounded confidence growth: cap 없이 +0.05 누적 — 매 1.0 saturation. cap 0.99.
• Decay-only no-bump: stale 만 잡고 fresh 강화는 없음 — graph 가 균질하게 늙음.

🧪 검증 / 중복

• Verified (in-house spec, CLEANUP_SPEC.md).
• 신뢰도 A.

🕓 Changelog

날짜	변경
2026-05-08	Phase 1
2026-05-10	Manual cleanup — full content for P-Reinforce framework

🛠️ 적용 사례 (Applied in summary)

🔎 코드베이스 근거 (자동 추출 — E:\Wiki 레포)

실제 구현/사용 위치:

• Datacollect/src/components/EmailPanel.tsx:17 — * Gmail 읽기전용 연결 → 최근 스레드 수집 → 스레드별 P-Reinforce wiki 합성 →
• Datacollect/scripts/web_extract.mjs:5 — * P-Reinforce v3.0 위키 문서로 LLM 합성한다.
• connectai/src/retrieval/terminologyBlock.ts:5 — * P-Reinforce vs p-reinforce, Chronicle vs 크로니클.
• connectai/src/features/datacollect/handlers.ts:424 — [Omitted long matching line]

관련 커밋:

• connectai eeb527c feat(datacollect): /youtube 개편·/wikify 신규·출력 위생 (v2.2.48)
• connectai a714017 feat(engine): complete stability overhaul - added state resume, deduplication, and P-Reinforce formatting
• Datacollect 4e00342 feat(wiki): RAG 포맷 강화 + 링크 해소 도구

자동 생성: code_grounding.mjs · 재실행 시 갱신됨