bluemsi/connectai
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
375 Commits 1 Branch 0 Tags
d39eb27c905598365f20360f78982fa8c17c5743
Commit Graph

46 Commits

Author SHA1 Message Date
koriweb d39eb27c90 feat(retrieval): 청킹/평가 하니스 + 검색 인덱스 개선 
- src/retrieval/chunker.ts: 문서 청킹 로직 추가
- src/retrieval/evalHarness.ts + src/extension/evalCommands.ts: 검색 품질 평가 하니스
- brainIndex.ts / retrieval/index.ts / memoryContext.ts: 인덱싱·컨텍스트 빌더 개선
- config.ts / extension.ts / sidebarProvider.ts / package.json 갱신
- ADR-0030~0032 및 개발 기록, .astra 런타임 상태 동기화

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
 2026-06-08 19:27:10 +09:00
koriweb 7bec20620a refactor: v2.2.195-201 — slashRouter god-file 해체 (–95%) + 인프라 5개 추출 
아키텍처 감사 결과 HIGH 2건 + MED 2건 + LOW 1건 — 7 라운드 정리 시리즈.
기능 변경 없음, 순수 구조 정리.

**slashRouter.ts: 4,174 → 201줄 (–3,973, –95%)**
**agent.ts: 1,617 → 1,551줄 (–66, –4%)**

v2.2.195: eventSourcedStore + SystemPromptBlock registry
  - createEventStore<E>(opts) — 4 store (customers/hire/runway/feedback) I/O 240줄 중복 제거
  - _turnCtx 5 named string field → 1 Map<string, string> (새 verification block 추가 25곳→1곳)
  - buildAstraModeSystemPrompt: 5 ternary gate + 5 위치 → 1 for-loop join

v2.2.196: trackers cluster split
  - src/features/teamops/handlers/_shared.ts (fmtKrw/parseAmount/daysUntil/parseTaskOwner/stageEmoji/STAGE_ORDER/TERMINAL_STAGES)
  - src/features/teamops/handlers/trackers.ts (runway/customers/hire)
  - src/features/teamops/handlers/index.ts (barrel)
  - extension.ts 에 side-effect import (순환 import 회피)

v2.2.197: mtimeFileCache + PostAnswerHook registry
  - src/lib/mtimeFileCache.ts — createMtimeFileCache<T>(name, parse) (terminologyBlock + termValidator 2-cache invariant 자동화)
  - src/agent/postAnswerHooks/{types,index}.ts — Devil/SelfCheck/TermValidator 3 _maybeX method → 1 runPostAnswerHooks(ctx) loop
  - agent.ts –66줄

v2.2.198: dashboards cluster split
  - src/features/teamops/handlers/dashboards.ts (morning/evening/cohort/weekly)

v2.2.199: coordination + communication clusters split
  - src/features/teamops/handlers/coordination.ts (task/decisions/onesie/blocked/standup)
  - src/features/teamops/handlers/communication.ts (draft/feedback)
  - callLmSynthesis export 노출 (communication 이 사용)
  - 옛 parseTaskOwner local 정의 삭제 (_shared.ts 사용)

v2.2.200: system cluster split
  - src/features/system/handlers.ts (memory/glossary/help)

v2.2.201: datacollect cluster split + LLM 인프라 추출
  - src/features/datacollect/handlers.ts (research/benchmark/youtube/blog/wikify/meet)
  - src/features/datacollect/llm.ts (callLmSynthesis + repairKoreanGlitches + bridgeErrorRemedy)
  - slashRouter import 4개로 축소: vscode/logInfo/getBridgeBaseUrl/bridgeErrorRemedy

**최종 slashRouter (201줄):**
- REGISTRY Map + registerSlashCommand/listSlashCommands/isSlashCommand
- handleSlashCommand (dispatcher + 에러 처리)
- Webview interface + chunk helper
- getRecentSlashCommands ring buffer (actionability scoring 용)

**미래 부담 감소 metrics:**
- 새 슬래시 명령: god-file 끝에 함수 + register → 1 파일 + 1 register call
- 새 verification block: 5곳 편집 → 1 set call
- 새 event store: 60줄 boilerplate → createEventStore 한 줄
- 새 post-answer hook: 3 step → 1 push
- 새 mtime cache: Map + invariant 관리 → createMtimeFileCache 한 줄

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
 2026-06-01 11:55:22 +09:00
koriweb 15a34e0889 feat: v2.2.194 — Post-gen Term Validator (결정론적 글로서리 검증) 
v2.2.192 Terminology Dictionary 가 *instructional* 지시 (LLM 에게 표준 표기 사용 권유)
였다면, 이번엔 *deterministic* 검증 — LLM 이 지시를 안 따랐을 때 결정론적 정규식 스캔.

신규 모듈: src/agent/termValidator.ts
- parseGlossary() — .astra/glossary.md 정규식 파싱 (mtime 캐시)
  Pattern 1: **Canonical** (X: typo1, typo2, ...) — typo 등장 시 "→ Canonical 권장"
  Pattern 2: H2/H3 "금지/비추/forbidden/avoid/don't" 섹션의 - ❌ "phrase"
- validateTermUsage() — 정규식 스캔 + 발견 횟수
- formatTermValidatorFooter() — markdown 한 줄 footer

False-positive 필터:
- 한글 1음절·영문 1자·공백 포함 토큰 제외
- 영문 단어 경계 매치, 한글 substring

Wiring:
- agent.ts _maybeRunTermValidator — Self-Check 직후, swallow 패턴
- /glossary reload — Term Validator 캐시도 함께 비움

신규 설정: g1nation.termValidatorEnabled (기본 true)

Footer 누적:
- v2.2.191 🔍 Self-check (LLM 호출, opt-in)
- v2.2.194 🔤 Term validator (정규식, on by default)

시너지: Terminology Dictionary(instructional, 작성 중) + Term Validator(deterministic,
작성 후) → 사용자가 .astra/glossary.md 한 곳만 관리하면 2단 자동 동작.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
 2026-05-29 16:38:56 +09:00
koriweb 990ea0ae5f feat: v2.2.173-193 — 4인 팀 운영 슬래시 13개 + ASTRA 검증 엔진 6종 
4인 팀 운영 슬래시 (v2.2.173~189):
- 일과 리듬: /morning, /evening, /weekly, /standup
- 트래커 (event-sourced .astra/*.jsonl): /runway, /customers, /hire
- 작업·결정: /task, /blocked, /onesie, /decisions
- 외부 출력: /draft, /feedback
- 분석: /cohort (MoM 추세)

ASTRA 추론·검색 엔진 (v2.2.183~192):
- v2.2.183 Conflict Surface — scoring.conflictSeverity 를 [CONFLICT WARNINGS] 블록으로
  서피스 + 교차-문서 발산(Jaccard) 감지
- v2.2.184 Chain-of-Verification — [VERIFICATION CHECKLIST] 답변 작성 전 그라운딩 자기 점검
  (instructional, strictMode 옵션)
- v2.2.185 Actionability Scoring — 최근 슬래시 명령 + 열린 파일 신호로 검색 결과 재가중
- v2.2.186 Temporal Markers + Distillation Loop — LongTerm/Episodic 만료 필터 +
  30일+ stale episode → LongTerm 'episode-digest' 승급 (수동 /memory distill + 세션 종료 자동)
- v2.2.187 Hierarchical Context Window + LLM Semantic Re-rank — 3-level 추상도 매칭
  + 토큰 예산 통과 후 LLM 1회로 의도-부합 재정렬 (opt-in)
- v2.2.190 Intent Clarification + Citation Trace — 모호 차원 감지 시 역질문 우선
  + 답변 끝 사용 출처 한 줄 정리
- v2.2.191 Post-hoc Self-Check — 답변 완료 후 별도 LLM 호출 1회로 답함/그라운딩/모순 평가,
  footer 한 줄로 표시 (opt-in, semantic re-rank 와 같은 안전 fallback 패턴)
- v2.2.192 Terminology Dictionary — .astra/glossary.md 사용자 편집 파일 + Term Check
  지침 통합 + /glossary init/path/reload
- v2.2.193 /help — 카테고리별 명령 목록 + 6종 verification 블록 현재 on/off

신규 모듈:
- src/retrieval/{conflictBlock,coveBlock,actionabilityScoring,hierarchicalLevel,
  semanticRerank,intentClarification,citationTrace,terminologyBlock}.ts
- src/memory/distillation.ts + types.ts 에 expiresAt/promoted/episode-digest 추가
- src/agent/postHocSelfCheck.ts
- src/features/{customers,feedback,hire,runway}/*.ts (event-sourced stores)

ASTRA 검증 5종 자동 주입 (buildAstraModeSystemPrompt, casual 모드 제외):
[INTENT CLARIFICATION GUIDANCE] (답변 시작 전) → [TERMINOLOGY DICTIONARY] +
[CONFLICT WARNINGS] + [VERIFICATION CHECKLIST] (작성 중) → [CITATION TRACE] (끝)
+ 6번째: Post-hoc Self-Check footer (답변 완료 후, opt-in)

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
 2026-05-29 16:05:30 +09:00
koriweb d206293a19 feat(stocks): v2.2.160-161 — 저평가 강조 + 224일선 회복 + 낙폭과대 키워드 
영상(주식단테 시리즈) 기준을 /stocks discover에 정량 매핑:

v2.2.160:
- 저평가 키워드 2단계 추가 (PBR ≤ 1.0 = 저평가, ≤ 0.7 = 초저평가)
- 정렬 타이브레이커: 통과 키워드 수 desc → PBR asc
- 224회복 보너스 (가격 only): MA224 돌파 + 최근 30일 중 5일+ 아래에 머문 적
- yahooClient: fetchYahooHistory + evalMa224Recovery 신설

v2.2.161:
- 224회복 거래량 검증 추가 (최근 5일 평균 ≥ 60일 평균 × 1.2) — 거짓 돌파 필터
- 신규 낙폭과대 키워드: 1년 고점 대비 -25% AND 60일 저점에서 +10%
- yahooClient: YahooHistory에 volumes, evalDropRecovery 신설

chronicle: ADR-0025 추가.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
 2026-05-27 10:10:09 +09:00
g1nation 0712014fcb chore: v2.2.73 — ASTRA-DEBUG 로그 레벨 + webview CSP font-src 보강 
- ASTRA-DEBUG 정상 흐름 로그를 console.error → logInfo/console.log 로 강등
  (chatHandlers, extension, slashRouter): DevTools에 ERR로 찍히던 오탐 제거
- sidebar webview에 명시적 CSP meta 추가 + font-src에 data: 허용
  (sidebar.html, sidebarProvider._getHtml): VS Code outer iframe이 codicon.ttf를
  data:font/ttf 로 inject하면서 기본 CSP에 막혀 매 prompt 마다 violation
  경고가 찍히던 문제 해소
- 누적된 LM Studio / agent / 컨텍스트 매니저 / 테스트 갱신 동반

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
 2026-05-23 15:52:19 +09:00
koriweb 49f941386f feat: v2.2.63 — 한국어 오타 최소화 (채팅 temperature 설정 + anti-glitch 샘플링) 
- streamer.ts: LM Studio SDK 호출에 topP/topK/minP/repeatPenalty 추가
  — 저확률 오답 토큰을 잘라 한글 음절 깨짐(붕괴→붕점) 억제
- 채팅 기본 temperature 0.7 → 0.3 (분석/업무형 답변 안정화)
- 신규 설정 g1nation.chatTemperature — Settings 패널 '고급' 섹션에서
  조절 가능 (config.ts / settingsPanelProvider / settings-panel.html+js)

chronicle 기록(ADR-0022, ADR-0023) 포함.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
 2026-05-22 19:09:01 +09:00
koriweb b0530db6f4 chore: ASTRA 런타임 기록 갱신 
소스 코드 변경 없음 — ASTRA가 자동 생성한 산출물만 포함:
- chronicle: ADR-0021 추가, timeline.md 갱신
- project-context 스캔 캐시 갱신

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
 2026-05-22 17:00:28 +09:00
koriweb 745ebc57f6 Update project files 2026-05-22 15:26:10 +09:00
koriweb 8016ef18fa Update project files 2026-05-22 15:00:14 +09:00
g1nation 86cacaeb03 Update ConnectAI codebase 2026-05-18 08:15:01 +09:00
g1nation 961e2cb4ea v2.2.16: Astra Office UI Overhaul & Operations Floor 2026-05-16 22:21:09 +09:00
koriweb 6f098e0ecc chore(release): v2.2.11 - Cross-Project Build Optimization & Stability Enforcement 2026-05-15 20:50:21 +09:00
g1nation 05d05a392c Resolve conflicts by preferring remote changes 2026-05-14 21:58:59 +09:00
koriweb 618b8d5b34 feat: Stabilize Company Suite & Self-Reflection logic, integrate new ADRs and bug records 2026-05-14 16:05:28 +09:00
g1nation 398703466f feat(architecture): add multi-subproject awareness and automatic context resync 
- Implemented subproject root resolution based on active editor hint
- Added debounced event listener for active editor changes to trigger chip status updates
- Updated sidebar provider to re-resolve active subproject root on every chip build
- This ensures correct architecture context is injected when working in a monorepo or multi-root-style parent folder
 2026-05-14 02:19:33 +09:00
g1nation 8da9532ca1 feat(engine): implement self-reflection (reflector) stage in multi-agent pipeline 
- Added ReflectorAgent for meta-cognition and critical review between Research and Writing
- Updated WriterAgent to explicitly address reflection critiques
- Introduced 'g1nation.enableReflection' configuration setting
- Added comprehensive integration tests for the self-reflection stage
- Documented design decisions in ADR-0010 and related discussion records
 2026-05-14 01:47:28 +09:00
g1nation b6899851c3 release: v2.0.3 - AI 1-Person Company Engine & Business Intelligence 2026-05-13 23:22:00 +09:00
g1nation c40571b7ef release: v2.0.2 - Structural Integrity & Automated Context Management 2026-05-13 22:34:44 +09:00
g1nation 7e99283f17 docs: update chronicle and implementation-4 records 2026-05-13 00:50:50 +09:00
g1nation b7ea805c07 chore: version up to 2.80.40 and package with ADR-0008 2026-05-13 00:44:57 +09:00
g1nation d2269297ea chore: version up to 2.80.39 and package with UI/config polish 2026-05-13 00:39:28 +09:00
g1nation eb36cec050 chore: version up to 2.80.38 and package with refined recovery 2026-05-13 00:15:45 +09:00
g1nation d899daa118 Update Astra/Agent state - 2026-05-10 22:26:50 2026-05-10 22:26:50 +09:00
g1nation f20388e2d5 chore: include internal agent state and resilience artifacts 2026-05-05 22:15:26 +09:00
g1nation 466e9e4d5f feat: ConnectAI structural hardening and retrieval precision improvements 2026-05-05 21:37:45 +09:00
g1nation cf10d14148 feat: Intelligent Resilience & Trust Reporting (v2.77.2) 2026-05-05 17:04:27 +09:00
g1nation 6470e23d73 [UX] Final alignment with user-defined 'Summary-Detail-Suggestion' output format 2026-05-05 16:25:04 +09:00
g1nation fc07e00f0c [Core] Disable automatic appending of redundant headers and internal logs in agent.ts 2026-05-05 16:19:02 +09:00
g1nation 76ec4624a8 [UX] Mass overhaul: Remove internal logs/questions and focus on actionable file-level guidance 2026-05-05 16:11:05 +09:00
g1nation f4c22bda54 [UX] Refactor system prompt for 'Verdict -> Proof -> Action' optimized output structure 2026-05-05 15:51:20 +09:00
g1nation 83e2bf10e5 chore(branding): rebrand extension to g1nation & Antigravity Edition 
- Updated publisher to g1nation.
- Removed all references to Jarvis and connectailab.
- Rewrote README.md to emphasize Personal Intelligence Layer for Antigravity & VS Code.
- Re-packaged v2.65.0 with new identifier (g1nation.astra).
 2026-05-04 23:01:04 +09:00
g1nation 71e39ad78e feat(core): upgrade to v2.65.0 with Cognition Layer & Proactive Advisor 
- Integrated v4.0 Operational Policy into AgentEngine and AgentExecutor.
- Added Context Amplification for policy-driven reasoning.
- Implemented Proactive Advisor for next-action decision forks.
- Added CognitionAudit diagnostics for real-time policy monitoring.
- Updated test suites to support dual-execution cognition patterns.
 2026-05-04 22:42:08 +09:00
g1nation 1395bbcdae feat(formatter): enforce implementation code snippet section in wiki artifacts 2026-05-04 15:58:47 +09:00
g1nation e7b939cd7c feat(engine): introduce agent handoff tracing and data integrity validation based on Astra analysis 2026-05-04 13:46:15 +09:00
g1nation 215c5f9457 feat: v2.62.0 - Astra Autonomous Loop (AAL) foundation & enhanced file analysis 2026-05-04 12:58:43 +09:00
g1nation 7643362080 Feat: Implement local path code review preflight and add system prompt tests 2026-05-02 18:37:39 +09:00
g1nation da4ebe3942 Feat: Enhance query intent search and answer format readability 2026-05-02 18:20:22 +09:00
g1nation fcc07e013e Feat: Implement Project Claim Output Brake and refine agent reasoning 2026-05-02 18:06:28 +09:00
g1nation f45225b29a Feat: Implement Project Chronicle Guard Policy and Second Brain Trace enhancements 2026-05-02 18:00:10 +09:00
g1nation 6c83a570ff Release: v2.36.4 - Datacollector Knowledge Sync 2026-05-02 17:51:07 +09:00
g1nation 70a86a3228 Fix: Repository URL in README and package.json 2026-05-02 17:01:02 +09:00
g1nation 04e81c3abf Release: v2.36.1 - Action Queue Optimization 2026-05-02 16:34:45 +09:00
g1nation f874ae6152 Release: v2.36.0 - P-Reinforce v3.0 Standard Integration 2026-05-02 16:26:35 +09:00
g1nation 0a58d5127a Bump version to 2.35.1: Second Brain Trace Collapsible UI. 2026-05-02 16:14:36 +09:00
g1nation 8bb8c065d7 Bump version to 2.35.0: Knowledge Resilience & Standardization Milestone. 2026-05-02 13:18:07 +09:00