hyungi 677a59b422 fix(hier): _ENG 매처 소문자 문장연속 가짜 절 차단 + 단위테스트 (asme-item-decomp D1) ...

영문 구조 헤딩 매처가 본문 'Part III to demonstrate…'·'Section I or Section VIII…'
같은 소문자 문장연속을 가짜 절로 잡던 것 차단. 식별자 뒤 선택 제목은 대문자/괄호/숫자로
시작해야 헤딩 인정. ATX 파트(# PART PG)·항목(#### PG-1)은 ATX 우선이라 무영향.
단위 11/11(음성·양성·ATX보존·통합 + 기존 7) + held-out 실데이터 회귀(5180 가짜절 1건 제거·
5206/5120/5130 무영향·added 0). CHUNKER_VERSION 유지(hier-rule-v1, D0a 결정).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

2026-06-17 08:28:06 +09:00

..

api

feat(search): /ask/react endpoint with Qwen native tool calling ReAct loop

2026-05-22 13:43:47 +00:00

calibrate_fixtures

feat(scripts): Phase 3.5 — calibrate_ask.py CLI (Q0~Q8 + render + FP CSV)

2026-04-17 08:11:06 +09:00

eid

ops(ai)!: 맥미니 생성 모델 Qwen3.6-27B-6bit 전환 + 생성 LLM 홀드 해제

2026-06-11 17:19:35 +09:00

fixtures

feat(papers): B-3 PR3 — OpenAlex 백본 수집기 (scaffold-first, signal-only, per-run cap)

2026-06-13 22:30:36 +00:00

hier_decomp

fix(hier): _ENG 매처 소문자 문장연속 가짜 절 차단 + 단위테스트 (asme-item-decomp D1)

2026-06-17 08:28:06 +09:00

load/fixtures

ops(gpu-health): GPU 서비스 health/smoke 표준화 + synthetic VRAM 피크 가드

2026-05-14 09:42:07 +09:00

phase3_5_eval

feat(ask): Phase 3.5a guardrails (classifier + refusal gate + grounding + partial)

2026-04-10 08:49:11 +09:00

policy

fix(policy): use container-compatible imports (drop app. prefix)

2026-04-24 09:42:24 +09:00

scripts

feat(chunk): Phase 1.2-E reindex 스크립트 추가

2026-04-08 12:31:29 +09:00

search_eval

test(eval): Phase 2A eval 산출물 — baseline exact 0.6315 vs qwen06/-0.041 qwen4/-0.032 qwen4m/-0.033 (no-go)

2026-06-12 05:53:20 +00:00

services

feat(search): /ask/react endpoint with Qwen native tool calling ReAct loop

2026-05-22 13:43:47 +00:00

__init__.py

feat: scaffold v2 project structure with Docker, FastAPI, and config

2026-04-02 10:20:15 +09:00

_worker_pool_helpers.py

refactor(worker-pool): Registry-1B test fixture — NullPool helper standalone

2026-05-19 12:43:53 +09:00

conftest.py

feat: scaffold v2 project structure with Docker, FastAPI, and config

2026-04-02 10:20:15 +09:00

test_arxiv_collector_units.py

feat(papers): B-3 PR2 — arXiv 키워드 필터 수집기 (signal-only, per-run cap)

2026-06-13 22:10:25 +00:00

test_ask_eval_auth.py

feat(ask): Phase 3.5 A0 — ask_events source/eval_case_id + eval auth boundary

2026-04-17 08:11:06 +09:00

test_b4_license_watch.py

fix(safety): B-4 리뷰 반영 — 단일 술어 중앙화 + study/briefing 경로 커버

2026-06-13 14:52:04 +09:00

test_briefing_historical.py

fix(briefing): backfill country_perspectives[].article_ids from cluster members

2026-05-12 13:15:26 +09:00

test_c1_decorate.py

feat(safety): C-1 후속 — version_status decorate + facets 집계

2026-06-13 15:07:57 +09:00

test_corpus_variant.py

feat(search): corpus_variant + exact_knn measurement dispatch (replace-diagnose c4+c5)

2026-05-25 05:37:15 +00:00

test_crawl_cycle2_shapes.py

fix(news): 304 를 redirect 로 오인하던 버그 — is_redirect → has_redirect_location

2026-06-11 06:32:15 +09:00

test_crawl_cycle3_shapes.py

fix(news): 연결 재시도 2회로 보강 — 드랍이 연결 단위 랜덤(재시도 1회도 연속 피격 실측) + 빈 에러 로그 repr

2026-06-11 07:54:13 +09:00

test_explanation_cap.py

fix(tests): explanation cap test setup — 한글 chunk 길이 부족 보정

2026-05-02 08:35:34 +09:00

test_fair_share.py

ops(pipeline): fair-share 번들 — drain classify 합류 + deep 맥미니 폴백 + mlx 게이트 동시 2

2026-06-12 06:56:02 +09:00

test_freshness_decay.py

feat(search): PR-RAG-Time-1 freshness decay (news/law_monitor)

2026-05-03 08:38:09 +09:00

test_grounding_fabricated_number.py

feat(grounding): Phase 3.5 B1 — unit-aware fabricated_number + bound semantics

2026-04-17 08:11:06 +09:00

test_internal_worker_authz.py

refactor(worker-pool): Registry-1B test fixture — NullPool helper standalone

2026-05-19 12:43:53 +09:00

test_internal_worker_endpoints.py

refactor(worker-pool): Registry-1B test fixture — NullPool helper standalone

2026-05-19 12:43:53 +09:00

test_kosha_fatal.py

feat(safety): B-2 KOSHA 사망사고 속보 수집기 (callApiId=1040)

2026-06-13 13:42:12 +09:00

test_laptop_worker_bot_auth.py

feat(worker-pool): Registry-1B Pull 활성화 (auth + worker_jobs + 5 endpoint)

2026-05-19 08:54:07 +09:00

test_macbook_offload_deep_slot.py

test(drain): classify 합류 반영 — 거부 케이스를 extract 로 교체

2026-06-12 07:22:47 +09:00

test_marker_image_persist.py

feat(markdown): persist extracted images with auth routes

2026-05-10 14:05:41 +09:00

test_openalex_collector_units.py

feat(papers): B-3 PR6 — OpenAlex ISSN 소스 시드 (KR/JP 안전 저널 직접 커버)

2026-06-13 22:42:30 +00:00

test_paper_doi_units.py

feat(papers): B-3 PR5 — 구매 PDF parent_doi 스탬프 (paper_doi_reconcile 통합)

2026-06-13 22:58:19 +00:00

test_phase2a_backend.py

feat(search): Phase 2A E-1 — Qwen 후보 3종 백필 CLI + eval 디스패처 확장 (마이그 328~333)

2026-06-12 08:29:53 +09:00

test_pipeline_hold.py

fix(news): digest/briefing 생성 LLM 타임아웃 게이트 단일소스화 + deep_summary 컨슈머 분리

2026-06-14 23:29:56 +00:00

test_priority_gate.py

ops(pipeline): fair-share 번들 — drain classify 합류 + deep 맥미니 폴백 + mlx 게이트 동시 2

2026-06-12 06:56:02 +09:00

test_query_rewriter.py

fix(search): Phase 2Q result dedup — apply_diversity unlimited path doc_id inflation 차단

2026-05-24 04:48:50 +00:00

test_queue_overview.py

feat(board): expose summarize_by_machine for offload visibility (A-1)

2026-06-13 13:54:39 +09:00

test_s1_dedup_b2.py

feat(documents): S1 dedup·office-md·storage scaffold (B/C/D/E)

2026-06-08 03:05:30 +00:00

test_s1_dedup_shape.py

feat(documents): S1-ADD dedup·원본명 3컬럼 + md_status success→completed 매핑 (A) + office→md PoC (C-1)

2026-06-08 03:05:30 +00:00

test_session_summary_guard_pattern.py

feat(study): Phase 4-D 운영 관찰 + confidence calibration

2026-05-02 07:33:57 +09:00

test_sr_schedule.py

refactor(study): SR 산술 sr_schedule.py 공용추출 (B1 — 카드 SR 토대)

2026-06-07 10:11:38 +09:00

test_statute_kr_adapter.py

feat(safety): B-1 PR① — law_monitor 스케줄 제거 + statute KR poll_changes + fixture 박제 (mig 356)

2026-06-13 09:01:21 +09:00

test_statute_lifecycle_units.py

feat(safety): B-1 PR② — fetch_version(payload 리스트) + ingest 4축 + 생애주기 잡 통째 + 부트스트랩

2026-06-13 09:37:51 +09:00

test_study_memo_card_guards.py

feat(study): 공부 암기노트 Phase 1 — 정정/삭제 훅 + needs_review 큐 + 알람 재료 (HR/A)

2026-06-07 08:08:55 +09:00

test_synthesis_failure_regate.py

fix(search): re-gate Tier 0 — synthesis self-refuse / timeout / empty answer 일관 처리

2026-04-17 08:29:49 +09:00

test_verifier_numeric_promote.py

feat(verifier): Phase 3.5 B2 — numeric_conflict promote (env flag) + Tier 4

2026-04-17 08:11:06 +09:00

test_worker_jobs_ownership.py

refactor(worker-pool): Registry-1B test fixture — NullPool helper standalone

2026-05-19 12:43:53 +09:00

test_worker_jobs_retry.py

refactor(worker-pool): Registry-1B test fixture — NullPool helper standalone

2026-05-19 12:43:53 +09:00

test_worker_jobs_skip_locked.py

refactor(worker-pool): Registry-1B test fixture — NullPool helper standalone

2026-05-19 12:43:53 +09:00

test_worker_jobs_smoke.py

refactor(worker-pool): Registry-1B test fixture — NullPool helper standalone

2026-05-19 12:43:53 +09:00

test_worker_recap_compaction.py

feat(worker-pool): Registry-1C cap 1MB + deterministic compaction

2026-05-19 12:55:51 +09:00

test_worker_recap_endpoint.py

feat(worker-pool): Registry-1C cap 1MB + deterministic compaction

2026-05-19 12:55:51 +09:00