bluemsi/connectai
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
355 Commits 1 Branch 0 Tags
ded3eea7ce44a5d279fc27c5d08109de2586868a
Commit Graph
100 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
g1nationandClaude Opus 4.7 ded3eea7ce feat: v2.2.74 → v2.2.82 — chunked writer + 코드 리뷰 패치 + /youtube 확장 
주요 변경:

[chunked writer 아키텍처 (v2.2.74~v2.2.75)]
- 5-stage 다중 에이전트(planner/researcher/reflector/writer/synthesizer)
  파이프라인 제거 → 단일 ChunkedWriter 의 outline → section[N] → polish
  3-step 으로 교체. 본문 분석에서 추상화 손실 / 토큰 폭증 문제 해소
- 답변 길이 자동 분기: 짧은 prompt 는 fast-path direct 1회 호출,
  본문 분석은 chunked. outline 빈 배열도 direct 폴백

[코드 리뷰 9개 항목 일괄 패치 (v2.2.76)]
- /research polling hang 방어 (heartbeat + status 정규화 + 연속 실패 abort)
- 회사 모드 dispatcher abort 신호를 AIService.chat 까지 전달
- bridgeFetch 에 onHeartbeat 콜백 도입 (slow endpoint 사용자 친화적)
- dead code 정리: reflectionPersister.ts 제거 + enableReflection 등 좀비 config 키
- parseOutline 의 empty vs fallback reason 명시적 분리
- chatHandlers 의 회사 모드 케이스 ~325줄을 src/sidebar/companyHandlers.ts 로 분리
- Intent Alignment 라운드 한도 도달 시 smart 모드 자동 진행
- LM Studio doSwitch unload 실패 시 currentModel 정리 + load 강행
- retrieval informationDensity → queryCoverage 정합화

[/youtube 채널 지원 (v2.2.77~v2.2.82)]
- 채널/플레이리스트 URL 자동 감지 + n:N 으로 영상 개수 지정 (최대 50)
- 채널 루트 URL 에 /videos 탭 자동 append (yt-dlp enumeration 정상화)
- 영상별 순차 처리 (queue 패턴) + i/N 진행 표시 + 마지막 통계 요약
- mode:info / mode:benchmark / mode:both 분석 모드 분기
  - info: 영상 내용을 지식 카드로 추출 (튜토리얼·강의·뉴스용)
  - benchmark: 4-렌즈 대본 역기획서 (콘텐츠 제작 벤치마크용)
  - both: 둘 다 (기본)
  - bare keyword 도 허용: /youtube <url> n:1 info
- bridge 에러 메시지 [object Object] 깨짐 수정 (구조화 에러 추출)
- "패키지 없음" 등 환경 의존성 에러에 자동 가이드 첨부

[Astra: Setup Datacollect Dependencies 명령 추가 (v2.2.80)]
- Python 자동 감지 + yt-dlp / youtube-transcript-api 자동 설치
- macOS PEP 668 환경 자동 폴백 (--user --break-system-packages)
- /youtube 등에서 패키지 미설치 감지 시 "Install Now" 버튼 notification

[테스트]
- tests/agentEngine.test.ts 를 chunked flow 에 맞춰 전체 재작성
- tests/resilience_stress.test.ts Scenario B/D 를 role-aware mock 으로 갱신
- 399/399 통과

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
 2026-05-23 23:13:21 +09:00
g1nationandClaude Opus 4.7 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
g1nationandClaude Opus 4.7 36db170844 feat: v2.2.64 — LM Studio 모델 발견/에러 표시 + macOS 셸 호환성 
- LM Studio 모델 dropdown을 SDK system.listDownloadedModels('llm') 으로
  조회하도록 변경. REST /v1/models 는 JIT 옵션이 꺼져 있으면 로드된 모델만
  반환하여 macOS 환경에서 dropdown 이 비거나 fallback 한 줄만 남던 문제 해결.
  SDK 실패 시 REST 로 자동 fallback.
- LM Studio 로드/언로드 실패를 readyBar 의 영속 segment 로 표시. 모델을
  다시 선택하면 clearLmStudioError() 로 해제.
- src/security.ts: PowerShell '&&' rewrite 를 win32 에서만 수행. macOS/Linux
  에서는 'if (\$?) { ... }' 가 zsh/bash 문법 오류라 명령 자체가 깨졌음.
- src/utils.ts: system prompt 에 OS 별 [ENVIRONMENT] 블록 동적 주입
  (셸/경로 스타일/체이닝 연산자). 'cd E:\\... ; ...' 같은 Windows 전용
  예시를 macOS 에서 그대로 따라하던 회귀 차단.
- 테스트 mock 에 listDownloaded() 추가.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-05-23 09:37:29 +09:00
g1nationandClaude Opus 4.7 dea5953f59 Astra v2.2.52 
- 채팅 기록 목록 누락 수정: 후처리 예외로 _saveCurrentSession 이 건너뛰던 회귀를
  try/finally 로 보장, _saveCurrentSession 자체도 throw 방지. 1인 기업 모드 업무
  턴(_runCompanyTurn)도 요청/보고서 쌍으로 기록 (_saveCompanyTurnSession).
- Self-Reflector 실행 검증 크로스플랫폼화: .py 는 python3 자동 탐지, .ts 는 로컬
  node_modules/typescript/bin/tsc 직접 호출.
- 버전 2.2.52 상향 + package-lock 동기화 + 재패키징.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-05-20 23:48:39 +09:00
g1nation 86cacaeb03 Update ConnectAI codebase 2026-05-18 08:15:01 +09:00
g1nation 88664c7c6e v2.2.19: Cloud Model Providers Support (OpenRouter, Anthropic, Gemini) 2026-05-16 23:34:35 +09:00
g1nation c7b596f17a v2.2.18: Dynamic Office Auto-Layout & Legacy Cleanup 2026-05-16 23:13:40 +09:00
g1nation 84b2b0670d v2.2.17: Google Service Control & Astra Office Flow Layer 2026-05-16 22:51:15 +09:00
g1nation 961e2cb4ea v2.2.16: Astra Office UI Overhaul & Operations Floor 2026-05-16 22:21:09 +09:00
g1nation 9ca95ab997 v2.2.15: Astra Office Refactor & Multi-Service Integration 2026-05-16 22:07:06 +09:00
g1nation 9dcc98ad33 v2.2.14: Advanced Pixel Office Customization & Face Directions 2026-05-16 20:11:57 +09:00
g1nation c4f01fd6af v2.2.13: Pixel Office Interactive Editor & Core Refinement 2026-05-16 13:18:49 +09:00
g1nation dea106ce68 v2.2.12: Sync & Visual Polish Expansion 2026-05-16 12:38:39 +09:00
g1nation ed7e497194 chore: sync project context and chronicle metadata 2026-05-14 23:31:25 +09:00
g1nation cd22da8735 Release v2.2.1: Autonomous Task Resumption & Engine Resilience 2026-05-14 23:27:51 +09:00
g1nation e86e3177c7 Release v2.2.0: Milestone - Human-Centric UI & Workflow Evolution 2026-05-14 22:58:45 +09:00
g1nation d9d89e6db7 Release v2.1.9: Immersive onboarding and UX transformation 2026-05-14 22:39:13 +09:00
g1nation 6b10d002fa Release v2.1.8: Company Agent roster overhaul and UI polish 2026-05-14 22:25:48 +09:00
g1nation ac0085ab53 Release v2.1.7: Version up and packaging 2026-05-14 22:04:08 +09:00
g1nation 05d05a392c Resolve conflicts by preferring remote changes 2026-05-14 21:58:59 +09:00
g1nation f521c3f557 Release v2.1.2: Chronicle Repair & Context Stability improvements 2026-05-14 02:37:49 +09:00
g1nation a374aa703a chore(release): bump version to 2.1.1 and update patch notes 2026-05-14 02:21:58 +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 373abfd920 chore(release): bump version to 2.1.0 and update patch notes 2026-05-14 01:52:54 +09:00
g1nation c4abd3994c fix(sidebar): force architectureAutoAttach to true on explicit re-activation 
Fixed a bug where architectureAutoAttach would stay false even after an explicit attach action due to incorrect nullish coalescing logic.
 2026-05-14 01:50:19 +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 e075779635 release: v2.0.9 - System Synchronization & Distribution (2026-05-14) 2026-05-14 01:07:46 +09:00
g1nation 46b4a7bc5d style: final sidebar UI polish and cache update (2026-05-14) 2026-05-14 01:06:27 +09:00
g1nation 147536fb13 release: v2.0.8 - UX Persistence & Per-Agent Knowledge Mix (2026-05-14) 2026-05-14 00:56:20 +09:00
g1nation 8104caf8d9 release: v2.0.7 - Enhanced Telegram Reporting & File Visibility (2026-05-14) 2026-05-14 00:37:41 +09:00
g1nation f1d5dbf031 release: v2.0.6 - Intelligence & UX Optimization (2026-05-14) 2026-05-14 00:13:54 +09:00
g1nation 39386f90b5 release: v2.0.5 - Telegram Business Reporting & Core Resilience 2026-05-13 23:54:34 +09:00
g1nation 6784e85b7e release: v2.0.4 - Advanced Business Orchestration & UI Polishing 2026-05-13 23:32:29 +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 e85e11aac6 release: v2.0.1 - Advanced Knowledge Mix & Architectural Intelligence 2026-05-13 22:05:39 +09:00
g1nation c32b17377b Release: Version 2.0.0 - Major Milestone & Intelligence Evolution 2026-05-13 21:53:17 +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 6c4bc3494f chore: version up to 2.80.37 and package with response recovery 2026-05-12 23:55:00 +09:00
g1nation e0af15767a chore: version up to 2.80.36 and package with UI/UX refinement 2026-05-12 23:41:18 +09:00
g1nation f6b27a125b chore: version up to 2.80.35 and package with experience memory 2026-05-12 23:23:23 +09:00
g1nation 065e598cca chore: version up to 2.80.34 and package 2026-05-12 22:54:21 +09:00
g1nation 148bfb070b release: v2.80.33 - sync with agent repository reorganization 2026-05-11 13:26:44 +09:00
g1nation 6347a223a7 release: v2.80.32 - LM Studio SDK resilience & auto-recovery 2026-05-11 13:19:07 +09:00
g1nation 5d3df0816f chore: version up to v2.80.31, clean up agent logic, and fix tests 2026-05-11 13:02:06 +09:00
g1nation 3c2b62c018 chore: version up to v2.80.30 and package vsix 2026-05-11 12:44:38 +09:00
g1nation 789680ccb1 Build: Release v2.80.29 2026-05-10 22:57:03 +09:00
g1nation ec71014481 Build: Release v2.80.28 2026-05-10 22:41:35 +09:00
g1nation d899daa118 Update Astra/Agent state - 2026-05-10 22:26:50 2026-05-10 22:26:50 +09:00
g1nation 3220a126fd chore: bump version to 2.80.27 and update core features 2026-05-09 01:16:12 +09:00
g1nation 5ffb472d22 Update Astra: v2.80.19 - Refactoring Sidebar, LM Studio integration, and new tests 2026-05-08 23:14:47 +09:00
g1nation d083177d95 docs: add architectural refactoring roadmap based on technical debt audit 2026-05-08 01:29:03 +09:00
g1nation d451a082dd feat: refactor AI engine logic, remove cross-engine fallback, add retry with backoff, and bump version to 2.80.18 2026-05-08 01:24:12 +09:00
g1nation f20388e2d5 chore: include internal agent state and resilience artifacts 2026-05-05 22:15:26 +09:00
g1nation 5716b9b216 fix: resolve integration test failures and resilience fallback logic 2026-05-05 21:56:54 +09:00
g1nation 855c235910 2.78.0 2026-05-05 21:37:45 +09:00
g1nation 466e9e4d5f feat: ConnectAI structural hardening and retrieval precision improvements 2026-05-05 21:37:45 +09:00
g1nation c2f17cfb03 feat: Resilience Hardening & Boundary Stress Validation (v2.77.3) 2026-05-05 17:17:00 +09:00
g1nation cf10d14148 feat: Intelligent Resilience & Trust Reporting (v2.77.2) 2026-05-05 17:04:27 +09:00
g1nation 037eafa02b [Core] Final user-optimized system prompt (v2.76.9) and test alignment 2026-05-05 16:35:33 +09:00
g1nation 154ae7dedc [Core] Consolidate system prompt rules and update tests 2026-05-05 16:32:15 +09:00
g1nation 7b8d5d1afd [UX] Refine follow-up question rules: Single Question & Answer-First policy 2026-05-05 16:26:54 +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 964c42f83f [UX] Clean up redundant reasoning headers for better readability 2026-05-05 15:56:08 +09:00
g1nation f4c22bda54 [UX] Refactor system prompt for 'Verdict -> Proof -> Action' optimized output structure 2026-05-05 15:51:20 +09:00
g1nation d333042e7c [RAG] Implement visual conflict and density metadata tags for enhanced context intelligence 2026-05-05 15:29:16 +09:00
g1nation f1b22c13b9 docs: marked roadmap Phase 4 as completed 2026-05-05 11:30:30 +09:00
g1nation 18021bd19d feat(scoring): implemented semantic context padding and optimized excerpting v2.76.0 2026-05-05 11:30:29 +09:00
g1nation fc7cc16e88 feat(retrieval): synchronized schema with conflict and density metrics v2.75.0 2026-05-05 11:24:18 +09:00
g1nation 518a5ed317 feat(scoring): completed roadmap Phase 1 & 2 with edge case stability v2.74.0 2026-05-05 11:20:44 +09:00
g1nation e6bc263872 feat(scoring): implemented tiered conflict severity system v2.73.0 2026-05-05 11:15:03 +09:00
g1nation 563e499324 feat(scoring): added comprehensive unit tests and refined bilingual tokenization v2.72.0 2026-05-05 11:10:31 +09:00
g1nation ca9fbf125a feat(scoring): integrated conflict detection and info density metrics v2.71.0 2026-05-05 11:03:06 +09:00
g1nation 0bac9d4b21 feat(scoring): implemented global caching and multi-stage density filtering v2.70.0 2026-05-05 10:57:40 +09:00
g1nation 8d6e510b00 perf(scoring): optimized retrieval engine with caching and IDF smoothing v2.69.0 2026-05-05 10:50:20 +09:00
g1nation 55c8e1c9dd fix(retrieval): resolved 'synonyms is not iterable' by using Map and Array.isArray v2.68.0 2026-05-05 10:39:34 +09:00
g1nation 177c10ee63 fix(compliance): enforced zero-emoji and unique headings policy v2.67.0 2026-05-05 10:36:23 +09:00
g1nation ccb5ca515e feat(cognition): integrated empathetic acknowledgment and reordered response flow v2.66.0 2026-05-05 10:28:45 +09:00
g1nation 421b2ce36a chore(branding): finalized g1nation & Antigravity branding for v2.65.0 2026-05-04 23:36:47 +09:00
g1nation 56500ebf98 chore(release): v2.65.1 - g1nation rebranding & Antigravity support 
- Finalized personal branding for g1nation.
- Integrated Antigravity platform support in README.md.
- Rebuilt VSIX package with new identifier (g1nation.astra).
 2026-05-04 23:11:43 +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 29f271d781 fix(assets): add standard background-clip for CSS compatibility 2026-05-04 16:07:52 +09:00
g1nation 8870c750a2 2.64.1 2026-05-04 15:58:48 +09:00
g1nation 1395bbcdae feat(formatter): enforce implementation code snippet section in wiki artifacts 2026-05-04 15:58:47 +09:00
g1nation a74c881375 test: clear cache before tests to ensure accurate benchmarks 2026-05-04 15:51:24 +09:00
g1nation a714017495 feat(engine): complete stability overhaul - added state resume, deduplication, and P-Reinforce formatting 2026-05-04 15:40:54 +09:00
g1nation 817d76c3fa feat(engine): implement state persistence, failure reason tracking, and quality scoring as per Astra review 2026-05-04 15:39:01 +09:00
g1nation 16106327b8 chore(release): bump version to 2.63.0 2026-05-04 13:53:46 +09:00
g1nation 9a05d3c217 fix(prompt): translate inferred user intent and blocking questions to Korean headings 2026-05-04 13:50:59 +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 445d530b63 feat: integrate unified RAG pipeline and bump version to 2.60.0 2026-05-04 11:00:01 +09:00
g1nation 0515dd625d release: v2.59.0 2026-05-03 21:11:33 +09:00
g1nation e9e1832db7 release: v2.58.0 2026-05-03 21:07:37 +09:00