jhogyu and Claude Fable 5
d8e5b241ac
docs(stage1-part3): add revision strategy spec superseding morning draft
...
- stage_1_part_3_개정_신전략서.md (48,467 B, sha16 0fa7c0ddf172dcd3):
Part 3 work spec rebuilt on post-BO-projection premises — deployment
origin extension_research/Default_Agent, builder roots already fixed,
sidecar deployment (50 files, manifest 371→426), deterministic
BO-attachment join (alias list resolution via legacy_alias_targets,
BO conservation equation, by_bo_id index), SG-11 join key = signal_id,
L0/L2 two-task design (no L1), input contracts I-1~I-14, regressions
L-a~L-s (22, 8 mandatory), D-4 decision pending user approval (P3-0a)
- verified by adversarial sub-agent loop: findings 13→5→1→1→1→0
(round 1 MAJORs: BO-attachment silent path, B1~B5 alias unwired,
regression vs _verify_asset discipline conflict, manifest superset
wording; rounds 4-5: active vs expected_runnable term unification,
EC-00 sidecar absence rule)
- closes carried-over C-7 (legacy signal names → canonical read set)
and C-8 (interface table updates) by design
- v.7/MEMORY.md: append entry 22
- 확장_최적워크플로우_연구_프롬프트.txt: session prompt log
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com >
2026-08-20 17:10:08 +09:00
jhogyu and Claude Fable 5
9d86372325
docs(stage1): rewrite Part 2 sections of analysis doc for BO projection round
...
- stage_1_part_1_and_2_updated_yaml_analysis.md: incremental Part 2 update
(122,642 B, sha16 3648dcd743353f71) — new integrated-spec metrics
(195,938 B / 3,315 lines / ec4c43027ad85195), revision rounds 4→5,
R0 projection/review-channel/status-policy/seed-rewrite-removal, F0
registry-union fallback + policy load, A0 10-asset/18-path gate,
three-tree asset geography (Default_Agent deployment origin, 155 files),
M-a~M-r regression table, deployment-origin dry run (pass2 29 writes,
BO.json 2 records value-checked), carried-over items D-1~D-6
- previous edition (2026-08-18, 106,290 B) rotated to
ver_8_yaml_candidates/outdated/..._old.md (2026-08-16 edition kept in
git history at 3d8d90dc )
- verified by independent sub-agent loop: findings 9 → 1 → 0; loop also
surfaced two asset-side facts now recorded in the doc (assembly
release_manifest stale for builder roots 6→10 edit; candidate overlay
559/560 identical)
- v.7/MEMORY.md: append entry 21
- 확장_최적워크플로우_연구_프롬프트.txt: session prompt log
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com >
2026-08-19 21:34:31 +09:00
jhogyu and Claude Fable 5
c01102724c
feat(stage1-part2): close C-1~C-11 with registry projection; add Default_Agent deployment tree
...
Part 2 v.8 개정 — 해결방안 §4 전건 실행:
- R0: project_to_bo_surface 신설 (v2 화이트리스트 ALLOWED_SEED_KEYS 제거,
반환 17키 고정), 검토 채널을 v3 review_items/unknown_or_unrouted_reviews로
연결 (원본 review_code 보존), seed 되쓰기 삭제 (기록자=워커 단독 선언 준수),
status 5종 정책 게이트 + fan-out 계획 slice/prompt sha 대조
- F0: BOType 폴백을 registry 합집합(bo_types_union)으로, 정규화 3종을
review_handoff에 보고, 투영 정책 sha 검증 반입
- A0: PART2_REQUIRED_ASSETS 10건 (배포 게이트 18경로)
- 신규 자산: Default_Agent/stage1_runtime/bo_surface_projection_policy.v1.json
- 공통 계약 한 문장으로 오버레이 legacy 지시 무력화 (색인·Part 1 봉인 무변)
- 빌더 manifest roots 6→10 (C-9), remedy 문구 현행화 (C-10)
Default_Agent/: 배포 원본 트리 신설 (실행 자산 154종 + runtime_manifest 371항).
검증: 함수 추출 before/after 재현, 예행 2패스 9단계 PASS (BO 2건 각 Evidence
2건, seed 무변, M-n 바이트 동일, E-999 BLOCK), 적대 검증 2회 (지적 5건 중
3건 반영·2건 조립본 동기화 회차로 이월) — 잔여 필수 수정 없음.
문서: 해결방안 v2 재검토판 (C-11 신규 확정), 해결내역서, 자산 배포 대응표,
MONITOR_SERVER_LOG 가이드. 구본은 outdated/에 보존.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com >
2026-08-19 19:10:36 +09:00
jhogyu and Claude Fable 5
3d8d90dcdb
chore: sync working tree — Stage 1 v.7 reorg, jikji indexes, claim-drafting docs
...
- Rename "Claude YAML"/"Codex YAML" folders to Claude_YAML/Codex_YAML in Stage_1 v.7
- Add Stage_1 v.7 extension research, results runs, and reference material
- Add/refresh .jikji search indexes (Case_02 and Default_Agent corpora)
- Add per-case-type claim drafting folders and PDFs (청구취지기재방법)
- Add 판례모음 crawling data (08_14, 08_18)
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com >
2026-08-19 14:07:35 +09:00
jhogyu
362a0d0242
docs: add claim drafting research and rule guides
2026-07-26 10:26:53 +09:00
jhogyu
262e82e124
fix(stage1): enforce Fact Ledger schema
...
- add a canonical Draft 2020-12 row schema
- validate candidate, patched, and reread rows
- document the v3-to-v4 rationale and fixture results
2026-07-22 13:48:25 +09:00
jhogyu
16b4259855
docs: analyze Fact Ledger output schema drift
2026-07-22 10:43:42 +09:00
jhogyu
e82c9e2848
chore: add Stage 1 v6 and v7 artifacts
2026-07-21 10:48:36 +09:00
jhogyu
32b1a35dca
docs: analyze complete Stage 1 workflow
2026-07-21 10:21:24 +09:00
jhogyu and Claude Opus 4.8
106e3c4efd
chore: untrack .DS_Store files (already gitignored)
...
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com >
2026-07-08 15:15:29 +09:00
jhogyu
e9b10f55fe
Merge branch 'main' of https://git.eroomai.com/jhogyu/Liti-agent-Development
...
# Conflicts:
# .serena/project.yml
# Case_02_Comparison_Research/.serena/project.yml
2026-07-08 15:14:40 +09:00
jhogyu
20c5235e68
Add new YAML prompts and update existing files for Stage 1 to Stage 2 transition
...
- Created new files for Stage 1 evaluation and revision strategy based on GPT and Claude recommendations.
- Added detailed revision plans addressing runtime issues in LES2 and optimizing workflows for Stage 2.
- Updated existing Stage 1 to Stage 2 transition prompts with additional search results and completion indicators.
- Enhanced clarity and structure in the documentation for better usability and understanding.
2026-07-08 15:11:05 +09:00
jhogyu
0f22300489
First Commit - Creating Liti-agent Development
2026-07-02 17:08:27 +09:00