- config.yaml: ai.models 에 triage (gemma4:e4b-it-q8_0, GPU Ollama,
context_char_limit=120k, timeout 30s) 신규. primary (MLX gemma-4-26b)
는 에스컬레이션 전용 역할 명시. fallback 을 gemma4:e4b 로 통일
(exaone 제거 이미 반영). classifier/verifier 는 optional 유지,
vision 은 optional 로 완화 (미사용 정리 준비).
- core/config.py: AIConfig 에 triage 필드 추가, vision 은 Optional 로
전환. AIModelConfig.context_char_limit + DeepSummaryBacklogConfig
(R2 backlog guard 임계치 ratio 0.3 / pending 5 / window 30min)
스키마 신설. load_settings 가 models.get("vision") graceful.
- ai/client.py: call_triage / call_primary / call_fallback 3-tier
진입점 신규. primary 는 caller 가 get_mlx_gate() 블록 안에서 호출
해야 한다는 계약 docstring. classify/summarize 는 DEPRECATED 주석
만 추가, 기존 호출부 (eval runner 등) 를 위해 유지.
PR-B B-0 Day 1. 기존 primary 경로 변경 없음 — 회귀 0 기대.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
frozen dataclass with from_stage / escalation_reasons / risk_flags /
distilled_context / original_pointers / synthesis_directives / user_intent /
draft_hint. JSON round-trip (to_json/from_json). to_system_injection() 으로
26B system prompt 에 주입할 텍스트 블록 생성 (risk_flags + directives +
distilled_context 순).
from_stage 는 whitelist 검증 (triage/classify/summarize_short/advice_trigger/
night_sweep/ask_pre/unknown). tuple 타입 강제 (mutability 방지).
PR-B 의 escalation_service 가 이 계약을 사용. PR-A 는 계약만 정의.
plan: ~/.claude/plans/wise-gliding-hippo.md
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- services/ocr/server.py: surya 0.17.x predictors 기반으로 재작성
(구 `from surya.ocr import run_ocr` 제거됨 → import error → 빈 텍스트 반환)
- NFC(DB 경로) vs NFD(NFS 파일시스템) 한글 정규화 mismatch 보정
- surya-ocr 버전 0.17.1 고정 (0.6~1.0 범위는 breaking change 노출)
- AIClient.ocr() NotImplementedError 제거 (호출처 0건, extract_worker 가
ocr-service HTTP 호출을 직접 사용)
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- extract_worker: LibreOffice 15000자 절단 제거 (full text 저장 원칙)
- classify_worker/summarize_worker: 요약 입력 15000→50000자 확대
- client.py: 길이 기반 Claude 자동전환 제거 (require_explicit_trigger 정책 준수)
_call_chat의 primary→fallback(exaone3.5) 체인은 유지
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
HIGH:
- Lock setup TOTP/NAS endpoints behind _require_setup() guard
(prevented unauthenticated admin 2FA takeover after setup)
- Sanitize upload filename with Path().name + resolve() validation
(prevented path traversal writing outside Inbox)
MEDIUM:
- Add score > 0.01 filter to hybrid search via subquery
(prevented returning irrelevant documents with zero score)
- Implement Inbox → Knowledge file move after classification
(classify_worker now moves files based on ai_domain)
- Add Anthropic Messages API support in _request()
(premium/Claude path now sends correct format and parses
content[0].text instead of choices[0].message.content)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Implement kordoc /parse endpoint (HWP/HWPX/PDF via kordoc lib,
text files direct read, images flagged for OCR)
- Add queue consumer with APScheduler (1min interval, stage chaining
extract→classify→embed, stale item recovery, retry logic)
- Add extract worker (kordoc HTTP call + direct text read)
- Add classify worker (Qwen3.5 AI classification with think-tag
stripping and robust JSON extraction from AI responses)
- Add embed worker (GPU server nomic-embed-text, graceful failure)
- Add DEVONthink migration script with folder mapping for 16 DBs,
dry-run mode, batch commits, and idempotent file_path UNIQUE
- Enhance ai/client.py with strip_thinking() and parse_json_response()
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Hyungi Ahn