jhogyu/Liti-agent-Development
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
40 Commits 1 Branch 0 Tags
527604d42ff0520d754c2948fecc7496c715964a
Commit Graph
29 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
jhogyu 527604d42f feat(stage2): implement S2_30 drafting 
Add release-bound claim-group drafting and reseal the shared P00, executor admission, and S2_00-S2_20 hash chain.
 2026-08-31 17:39:19 +09:00
jhogyu daab564e81 feat(stage2): implement S2_20 relief planner 
- add one inline deterministic MCP task and sealed planning assets
- reseal S2_00/S2_10 release hashes for the S2_20 handoff
- keep live and legal admission explicitly pending
 2026-08-31 14:02:15 +09:00
jhogyu 978e6a6b72 feat(stage2): integrate hybrid S2_10 
Bind structured S2_00 handoff to the inline-prompt S2_10 Agent and reseal the parent-child release chain.
 2026-08-31 01:11:40 +09:00
jhogyu 1b7d2d3a09 feat(stage2): run S2_00 through inline MCP 
Replace the unresolved host-loader invocation with one hash-bound Code Executor task so deterministic ingress has a concrete Agent execution path.\n\nBREAKING CHANGE: S2_00 no longer invokes stage2_loader.py. The legacy loader binding is reference-only and cannot authorize or provide fallback.
 2026-08-30 16:37:43 +09:00
jhogyu 388a6c0179 feat(stage2): add S2_00 AgentBackend spec 
Keep the adapter non-executable until the native loader primitive and signed runtime admission contracts are bound.
 2026-08-30 03:05:06 +09:00
jhogyu 0ac7223790 feat(stage2): implement S2_00 asset package 
Add the 141-file deterministic ingress package, implementation plan, and scoped project memory record. Keep runtime admission disabled until pending bindings, signatures, authority data, Stage 1 seals, and legal review are complete.
 2026-08-30 01:32:29 +09:00
jhogyu decd3280bc docs(stage2): add S2_00 asset inventory 2026-08-29 23:42:51 +09:00
jhogyu fef75bd30d docs(stage2): finalize v4 strategy and assets 
Preserve v3 contracts while integrating accepted audit findings. Document version-free runtime assets and independent verification evidence.
 2026-08-28 17:08:03 +09:00
jhogyuandClaude Fable 5 e35d979bb3 docs(stage2): v.3 전략 엄격 검증 eval 보고서 + 검증 원장 + MEMORY 
- eval_stage_2_optimal_update_strategy_v.3.md: 8차원 finder·refuter Workflow(176 sub-agent)와
  3-lens 독립 감사 2회로 v.3(sha fd2b39fb…)를 검증. 판정 CRITICAL 2·MAJOR 22·MINOR 36.
  v2-1 대비 LOST 15건(유류분 전환 계약·137 catalog blueprint·freshness·사죄광고 금지 등)과
  소장 작성층 신규 결함(cause-atom provenance, 갑 호증, 동시이행, 필수적 공동소송 등) 기록.
  법률 인용 20건 law.go.kr/scourt 직접 확인, 민법_지원림.pdf 쪽 단위 대조.
- evals/stage2_v3/eval_v3_verification_ledger.md: finder/refuter/critic 원장, 감사 1·2차,
  clean-slate 식별자 61종 부록.
- 2. Stage_2/MEMORY.md: 세션 요약·교훈 추가.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
 2026-08-28 09:07:11 +09:00
jhogyu e12dc59189 docs(stage2): v3 개정 전략 확정 
v2-1 평가와 사건종류별 규칙·요건사실 검색 흐름을 5-task DAG에 통합한다.

사해행위 자산 10종은 migration source로만 보존하고 독립 검증 2회 기록을 포함한다.
 2026-08-28 01:31:28 +09:00
jhogyuandClaude Fable 5 40ddd6ccd1 docs(stage1): part 1~4 작업분석서 4종 작성 (Stage 2 명세 설계 입력) + MEMORY ㊳㊴ 
- Analysis_Doc_stage_1_part_{1..4}_investrigation_final.md:
  DAG ASCII·task별 IO 전수·자산 표(.py/.txt 미러 병기)·sub-task 명칭/내역/목적·
  upstream-downstream 연결 이유/방식/필드 소비
- part별 독립 검증자 전수 대조 통과(라운드 p1=2·p2=3·p3=1·p4=2, 최종 결함 0)
- MEMORY.md: ㊳ Part 4 신작 검증 왕복, ㊴ 분석서 4종 작성 기록

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
 2026-08-23 21:52:02 +09:00
jhogyuandClaude Fable 5 e6f514be76 feat(stage1-part4): 사실원장 yaml 신작 (전략서 방식, 구 v3와 무관) + 자산 배포 
- stage_1_part_4_v.8.yml: F0 code 리듀서(배포게이트 13·봉인 3종·13인자 호출)
  → F1 flash-lite 예외 재정판정(amount 한정) → F2 code 최종 게이트/작성자
  (보존 등식 5종 재계수·닫힌 29키·handoff FINALIZED), 완전 직렬 DAG
- 신설 자산: fact_ledger_compiler(.py/.txt 미러)·fact_ledger_policy.v1·스키마 3종,
  게이트 사이드카 gates.json ×25 배포
- legal_effect_structures.schema: signal_manifest_transaction_id required 승격
- runtime_manifest 434→465항(전수 MISMATCH 0), 인계면 45→55행(C-7 폐쇄),
  stage_chain Part 4 구간 갱신, 조립본 동기화(파일만)
- 독립 검증 2회 왕복: 1차 FAIL(U4 3건·MINOR 2) 수정 후 재검증 PASS·결함 0
- 전략서·구축 요약서(§7.4 정정 및 SG-01 재봉인 레시피 포함) 수록

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
 2026-08-23 21:51:50 +09:00
jhogyuandClaude Fable 5 85fca071c0 feat(stage1-part2): special-law 배선·seed admission 도입 및 안정화 (Aug 21~22 디버깅 사이클) 
- prompt_compiler에 SLP(특별법 프로파일) 배선, prompt_composition_policy 갱신
- seed_admission_policy.v1 신설: R0 전체 스키마 검증을 4단 수용 등급으로 전환
- special_law_profiles/ 3종 + profile_ids.json 카탈로그 배포
- stage_1_part_2_v.8.yml: worker 모델 gemini-3.1-pro-preview 복원, 투영 정렬,
  slice event 식별자 정본화, S0 enum 어휘 명시, 시드 신선도 실물 근거화
- 개정 전 판본 8종 outdated/ 보존, 문제 분석 문서 5종 수록

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
 2026-08-23 21:51:29 +09:00
jhogyuandClaude Fable 5 31035d5757 fix(stage1): execute asset-triage v.2 confirmed items — P2 dead constants/comment, manifest +6, matrix removal 
- stage_1_part_2_v.8.yml (195,963 B, sha16 ec407309a5ab43f4): drop two
  dead R0 path constants (S0's own copies untouched); narrow the
  legacy_paths_forbidden header comment to old slice/seed paths and
  state that stage_a_context/source_universe/postb_* keep
  stage1_tmp/task_c_bo as canonical. R0 fragment synced; prior
  versions preserved under outdated/ (pre_asset_triage_fix)
- Default_Agent/runtime_manifest.json 426->432: register six unanchored
  Part 1 assets (component union, client_goal schema, two reference
  catalogs, determinism contract, activation cue digest) with
  runtime_artifact_count updated and round-trip serialization kept
- remove case_kind_domain_matrix.v2.json from deployment origin
  (byte-identical master kept in assembly tree; empty folders pruned);
  tree 210->209, listed∩tree 155 with zero hash mismatches
- stage_1_2_3_assets_distribution_location.md rewritten as the
  Default_Agent change record only; full survey kept as *_old.md
- Part 1|2 analysis doc: 10 targeted updates (sizes/sha, shifted line
  ranges A0 62-719 / B 720-849 / R0 850-1793, constant wording removed,
  §8 history row annotated with a dated note instead of rewriting)
- verified: 3-pass dry run PASS with BO.json and
  legal_effect_structures.json byte-identical to the previous round;
  adversarial sub-agent check 29 items, findings 1 -> 0
- v.7/MEMORY.md entry 26

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
 2026-08-20 17:10:09 +09:00
jhogyuandClaude Fable 5 2bd5a12902 docs(stage1): add Part 3 analysis report and asset-location problem triage v.2 
- stage_1_part_3_updated_yaml_analysis.md (41,948 B): full analysis of
  stage_1_part_3_v.8.yml — DAG, per-task IO with formats, asset deploy
  locations (.py/.txt mirrors included), sub-task purposes, upstream/
  downstream contracts; verified by sub-agent loop 6->1->0 findings
  (all MINOR; diagram order corrected to code-measured sequence)
- problems_identified_in_detecting_assets_location_v.2.md: re-verified
  all 8 items of the distribution survey §8 plus the 277-row manifest
  gap (1st-pass measurement + one independent sub-agent recheck, 9/9
  agreed). Two v.1 verdicts overturned with evidence: 277-file copy
  recommendation rejected (superset-ledger design documented in 4 docs;
  no gate scans those paths) and P3 header L24 "corruption" disproven
  via creation-commit byte identity. Confirmed problems: R0 dead
  constants, legacy_paths comment, 6 unanchored P1 assets (register
  rows directly in deployment-origin manifest, count field updated),
  plaintext Bearer token (rotation is the real fix — 402 files carry it;
  SKILL.md has no secret-injection syntax)
- includes source docs from survey round: stage_1_2_3_assets_
  distribution_location.md, problems_identified_...(v.1)
- v.7/MEMORY.md entries 24-25; session prompt log update

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
 2026-08-20 17:10:09 +09:00
jhogyuandClaude Fable 5 6c7c793b2a feat(stage1-part3): build Part 3 spec from registry per new strategy; deploy structure assets 
- ver_8_yaml_candidates/stage_1_part_3_v.8.yml (52,878 B): two-task stage
  (Task_C_LE_L0_structure_seed_reducer -> Task_C_LE_L2_final_structure_index_writer,
  no L1) built solely from registry and Part 1|2 outputs (zero Claude_YAML
  dependency); fragments P3-L0/L2 v1 block-identical to the integrated file
- Default_Agent deployment origin: new structure_index_compiler.py(+mirror),
  structure_index_policy.v1.json, two sealed schemas (unversioned filenames,
  pattern-only), 50 sidecar files copied byte-identical from assembly;
  runtime_manifest 371->426 (delta exactly 55, zero existing-row edits)
- interface table 34->45 rows (closes C-7: legacy signal names dropped from
  Part 3 consumers; closes C-8: client_goal registered, client_meeting
  consumer added in both duplicated rows), stage_chain Part 3 section,
  upper strategy chain/§4.2 updated for L1 absence
- verified: 3-pass dry run on deployment origin produces
  legal_effect_structures.json (theta 4, 6 records, SG-13 6/6 attached,
  BO 2/2 attached via source_domain+Legal_Keywords join, 3 conservation
  equations from source counts, 3 reverse indexes); 26-domain synthetic
  theta 56 / records 73 / modules 34, deterministic; regressions 22+2
  supplementary all PASS on copied variant trees; interface checker 0
  findings; adversarial sub-agent loop 5 findings -> 0
- P3-0a (D-4 approval) treated as granted by the user's execution order;
  assembly-side sync (builder registration, ledgers, receipt) deferred as
  one bundle with Part 2 carry-overs
- work record stage_1_part_3_개정작업내역서.md; v.7/MEMORY.md entry 23;
  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
jhogyuandClaude 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
jhogyuandClaude 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
jhogyuandClaude 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
jhogyuandClaude 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
jhogyuandClaude 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