g1nation
ded3eea7ce
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>
734 lines
38 KiB
JSON
734 lines
38 KiB
JSON
{
|
||
"name": "astra",
|
||
"displayName": "Astra",
|
||
"description": "The personal intelligence layer for Antigravity and VS Code. A private cognitive partner for deep project context, memory, and proactive strategic decision-making.",
|
||
"version": "2.2.82",
|
||
"publisher": "g1nation",
|
||
"license": "MIT",
|
||
"icon": "assets/icon.png",
|
||
"repository": {
|
||
"type": "git",
|
||
"url": "https://github.com/g1nations/locallm"
|
||
},
|
||
"engines": {
|
||
"vscode": "^1.80.0"
|
||
},
|
||
"categories": [
|
||
"Machine Learning",
|
||
"Programming Languages",
|
||
"Chat"
|
||
],
|
||
"keywords": [
|
||
"ai",
|
||
"local",
|
||
"ollama",
|
||
"gemma",
|
||
"llama",
|
||
"deepseek",
|
||
"offline",
|
||
"agent",
|
||
"code-generation",
|
||
"astra",
|
||
"copilot"
|
||
],
|
||
"activationEvents": [
|
||
"onStartupFinished"
|
||
],
|
||
"main": "./out/extension.js",
|
||
"contributes": {
|
||
"commands": [
|
||
{
|
||
"command": "g1nation.newChat",
|
||
"title": "Astra: New Chat",
|
||
"icon": "$(add)"
|
||
},
|
||
{
|
||
"command": "g1nation.exportChat",
|
||
"title": "Astra: Export Chat as Markdown"
|
||
},
|
||
{
|
||
"command": "g1nation.explainSelection",
|
||
"title": "Astra: Explain Selected Code"
|
||
},
|
||
{
|
||
"command": "g1nation.focusChat",
|
||
"title": "Astra: Focus Chat Input"
|
||
},
|
||
{
|
||
"command": "g1nation.showBrainNetwork",
|
||
"title": "Astra: Show Brain Topology"
|
||
},
|
||
{
|
||
"command": "g1nation.approval.focus",
|
||
"title": "Astra: Focus Approval Panel"
|
||
},
|
||
{
|
||
"command": "g1nation.scaffoldProject",
|
||
"title": "Astra: Scaffold New Project"
|
||
},
|
||
{
|
||
"command": "g1nation.telegram.setBotToken",
|
||
"title": "Astra: Set Telegram Bot Token"
|
||
},
|
||
{
|
||
"command": "g1nation.telegram.clearBotToken",
|
||
"title": "Astra: Clear Telegram Bot Token"
|
||
},
|
||
{
|
||
"command": "g1nation.telegram.testConnection",
|
||
"title": "Astra: Test Telegram Connection"
|
||
},
|
||
{
|
||
"command": "g1nation.settings.focus",
|
||
"title": "Astra: Open Settings Panel"
|
||
},
|
||
{
|
||
"command": "g1nation.skills.editKnowledgeMap",
|
||
"title": "Astra: Edit Agent ↔ Knowledge Map"
|
||
},
|
||
{
|
||
"command": "g1nation.openChat",
|
||
"title": "Astra: Open Chat (Editor Column)",
|
||
"icon": "$(comment-discussion)"
|
||
},
|
||
{
|
||
"command": "g1nation.setupDatacollect",
|
||
"title": "Astra: Setup Datacollect Dependencies (yt-dlp, youtube-transcript-api)",
|
||
"icon": "$(cloud-download)"
|
||
},
|
||
{
|
||
"command": "g1nation.lesson.create",
|
||
"title": "Astra: New Lesson (Experience Memory)"
|
||
},
|
||
{
|
||
"command": "g1nation.lesson.fromConversation",
|
||
"title": "Astra: New Lesson from Current Conversation"
|
||
},
|
||
{
|
||
"command": "g1nation.lesson.manage",
|
||
"title": "Astra: Browse / Manage Lessons"
|
||
},
|
||
{
|
||
"command": "g1nation.architecture.refresh",
|
||
"title": "Astra: Refresh Project Architecture Context"
|
||
},
|
||
{
|
||
"command": "g1nation.architecture.detach",
|
||
"title": "Astra: Detach Project Architecture Context"
|
||
},
|
||
{
|
||
"command": "g1nation.architecture.attach",
|
||
"title": "Astra: Attach Project Architecture Context"
|
||
},
|
||
{
|
||
"command": "g1nation.architecture.open",
|
||
"title": "Astra: Open Project Architecture Doc"
|
||
},
|
||
{
|
||
"command": "g1nation.company.toggle",
|
||
"title": "Astra: Toggle 1인 기업 Mode"
|
||
},
|
||
{
|
||
"command": "g1nation.company.manage",
|
||
"title": "Astra: Manage 1인 기업 Agents"
|
||
},
|
||
{
|
||
"command": "g1nation.company.openSessions",
|
||
"title": "Astra: Open 1인 기업 Sessions Folder"
|
||
},
|
||
{
|
||
"command": "g1nation.company.pixelOffice.open",
|
||
"title": "Astra: Open Pixel Office (Full Screen)"
|
||
},
|
||
{
|
||
"command": "g1nation.calendar.connect",
|
||
"title": "Astra: Google Calendar (iCal) 연결 📅"
|
||
},
|
||
{
|
||
"command": "g1nation.calendar.refresh",
|
||
"title": "Astra: Google Calendar 새로고침 📅"
|
||
},
|
||
{
|
||
"command": "g1nation.calendar.connectOAuth",
|
||
"title": "Astra: Google Calendar OAuth 연결 (쓰기) 🔐"
|
||
},
|
||
{
|
||
"command": "g1nation.devilAgent.toggle",
|
||
"title": "Astra: Toggle Devil Agent 🎭"
|
||
}
|
||
],
|
||
"keybindings": [
|
||
{
|
||
"command": "g1nation.focusChat",
|
||
"key": "cmd+l",
|
||
"mac": "cmd+l"
|
||
}
|
||
],
|
||
"menus": {
|
||
"editor/context": [
|
||
{
|
||
"command": "g1nation.explainSelection",
|
||
"when": "editorHasSelection",
|
||
"group": "1_modification"
|
||
}
|
||
]
|
||
},
|
||
"viewsContainers": {
|
||
"activitybar": [
|
||
{
|
||
"id": "g1nation-astra-activity",
|
||
"title": "Astra (g1nation)",
|
||
"icon": "assets/icon-activitybar.svg"
|
||
}
|
||
]
|
||
},
|
||
"views": {
|
||
"g1nation-astra-activity": [
|
||
{
|
||
"id": "g1nation-astra-launcher",
|
||
"name": "Astra (g1nation) Launcher"
|
||
}
|
||
]
|
||
},
|
||
"viewsWelcome": [
|
||
{
|
||
"view": "g1nation-astra-launcher",
|
||
"contents": "✦ **Astra** — 로컬 AI 인텔리전스 레이어\n\nChat 탭을 닫았을 때 여기서 다시 열 수 있습니다.\n\n[$(comment-discussion) Open Chat](command:g1nation.openChat)\n[$(add) New Chat](command:g1nation.newChat)\n[$(gear) Settings](command:g1nation.settings.focus)\n\n---\n\n**1인 기업 모드**\n\n[$(organization) Manage Agents](command:g1nation.company.manage)\n[$(folder-opened) Open Sessions Folder](command:g1nation.company.openSessions)\n\n---\n\n**Project Architecture**\n\n[$(file-text) Open Architecture Doc](command:g1nation.architecture.open)\n[$(refresh) Refresh Architecture](command:g1nation.architecture.refresh)\n\n---\n\n**Lessons / Knowledge**\n\n[$(lightbulb) Manage Lessons](command:g1nation.lesson.manage)\n[$(edit) Edit Agent ↔ Knowledge Map](command:g1nation.skills.editKnowledgeMap)"
|
||
}
|
||
],
|
||
"configuration": {
|
||
"title": "Astra",
|
||
"properties": {
|
||
"g1nation.multiAgentEnabled": {
|
||
"type": "boolean",
|
||
"default": false,
|
||
"description": "Enable Multi-Agent Workflow (Planner -> Researcher -> Writer) for complex tasks."
|
||
},
|
||
"g1nation.datacollectBridgeUrl": {
|
||
"type": "string",
|
||
"default": "http://127.0.0.1:3002",
|
||
"description": "Wiki/Datacollect MCP Bridge URL. /research, /benchmark, /youtube chat slash commands route here. The Bridge must be running (`npm run bridge` in the Datacollect project)."
|
||
},
|
||
"g1nation.datacollectSavePath": {
|
||
"type": "string",
|
||
"default": "",
|
||
"markdownDescription": "`/benchmark` 등 Datacollect slash 명령 결과물(markdown)을 저장할 폴더. **비워두면** Bridge 기본 위치(Bridge의 `WIKI_RAW_PATH` 환경변수)에 저장됩니다 — 코드/설정 어디에도 절대경로가 박히지 않습니다. 특정 폴더로 저장하려면 절대경로를 입력하세요. Astra Settings 패널의 'Datacollect' 섹션에서도 편집 가능."
|
||
},
|
||
"g1nation.datacollectCrawlDepth": {
|
||
"type": "number",
|
||
"default": 1,
|
||
"minimum": 0,
|
||
"maximum": 3,
|
||
"markdownDescription": "`/benchmark` 사이트맵 크롤 깊이 기본값. 0=루트만, 1=직속 자식, 2=손자, 3=깊은 크롤. 명령어에서 `depth=N`으로 그때그때 덮어쓸 수 있습니다. (단일 페이지 SPA는 깊이를 올려도 1페이지)"
|
||
},
|
||
"g1nation.datacollectMaxPages": {
|
||
"type": "number",
|
||
"default": 8,
|
||
"minimum": 1,
|
||
"maximum": 20,
|
||
"markdownDescription": "`/benchmark` 스캔 최대 페이지 수 기본값. 명령어에서 `pages=N`으로 덮어쓸 수 있습니다. Bridge에서 20으로 상한이 적용됩니다."
|
||
},
|
||
"g1nation.datacollectSynthesisTemperature": {
|
||
"type": "number",
|
||
"default": 0.1,
|
||
"minimum": 0,
|
||
"maximum": 2,
|
||
"markdownDescription": "`/benchmark` LLM 4-렌즈 합성의 temperature. 낮을수록(0.1) 환각·깨진 문자가 줄고 결과가 결정적이며, 높을수록 표현이 다양해집니다. 기본 0.1 권장."
|
||
},
|
||
"g1nation.chatTemperature": {
|
||
"type": "number",
|
||
"default": 0.3,
|
||
"minimum": 0,
|
||
"maximum": 2,
|
||
"markdownDescription": "채팅 응답 생성의 temperature. 낮을수록(0.2~0.3) 한국어 오타·깨진 토큰·환각이 줄고 결과가 안정적이며, 높을수록 표현이 다양해집니다. 분석·업무용은 0.3 권장."
|
||
},
|
||
"g1nation.memoryEnabled": {
|
||
"type": "boolean",
|
||
"default": true,
|
||
"description": "Enable layered memory injection before each model response."
|
||
},
|
||
"g1nation.memoryShortTermMessages": {
|
||
"type": "number",
|
||
"default": 8,
|
||
"minimum": 0,
|
||
"description": "Number of recent conversation messages included as short-term memory."
|
||
},
|
||
"g1nation.memoryMediumTermSessions": {
|
||
"type": "number",
|
||
"default": 5,
|
||
"minimum": 0,
|
||
"description": "Number of recent saved chat sessions included as medium-term memory."
|
||
},
|
||
"g1nation.memoryLongTermFiles": {
|
||
"type": "number",
|
||
"default": 6,
|
||
"minimum": 0,
|
||
"description": "Number of relevant Second Brain markdown files included as long-term memory."
|
||
},
|
||
"g1nation.ollamaUrl": {
|
||
"type": "string",
|
||
"default": "http://127.0.0.1:11434",
|
||
"description": "Base URL for Ollama or LM Studio. Default: http://127.0.0.1:11434"
|
||
},
|
||
"g1nation.defaultModel": {
|
||
"type": "string",
|
||
"default": "gemma4:e2b",
|
||
"description": "Default model name to use for chat requests."
|
||
},
|
||
"g1nation.requestTimeout": {
|
||
"type": "number",
|
||
"default": 300,
|
||
"description": "Request timeout in seconds. Default: 300"
|
||
},
|
||
"g1nation.contextLength": {
|
||
"type": "number",
|
||
"default": 32768,
|
||
"minimum": 2048,
|
||
"description": "Model context window in tokens (prompt + generation combined). Set this to the value your loaded model is actually running with in LM Studio / Ollama. Astra budgets prompt and output against this so it never overflows. Default: 32768"
|
||
},
|
||
"g1nation.maxOutputTokens": {
|
||
"type": "number",
|
||
"default": 4096,
|
||
"minimum": 256,
|
||
"description": "Upper bound on tokens generated per response. The effective limit is reduced automatically when the prompt is large so input + output stays within g1nation.contextLength. Default: 4096"
|
||
},
|
||
"g1nation.contextSafetyMargin": {
|
||
"type": "number",
|
||
"default": 2048,
|
||
"minimum": 0,
|
||
"description": "Tokens kept free as a safety buffer for token-count estimation error. Default: 2048"
|
||
},
|
||
"g1nation.contextOverflowPolicy": {
|
||
"type": "string",
|
||
"enum": [
|
||
"stopAtLimit",
|
||
"truncateMiddle",
|
||
"rollingWindow"
|
||
],
|
||
"default": "stopAtLimit",
|
||
"description": "Fallback behavior (LM Studio) if the prompt still exceeds the context window after Astra's own budgeting. 'stopAtLimit' fails clearly so you notice; 'truncateMiddle'/'rollingWindow' drop content silently. Default: stopAtLimit"
|
||
},
|
||
"g1nation.autoCompactHistory": {
|
||
"type": "boolean",
|
||
"default": true,
|
||
"description": "Automatically drop the oldest conversation messages from the request when the prompt would exceed the context budget (the on-screen chat history is unaffected). Default: true"
|
||
},
|
||
"g1nation.smallModelContextCap": {
|
||
"type": "number",
|
||
"default": 0,
|
||
"minimum": 0,
|
||
"description": "Optional safety knob, OFF by default (0). Some very small models (≤3B) emit an empty/EOS response when given a prompt near their context window even though it nominally fits. If you observe that with a tiny model, set this to e.g. 8192–16384: for ≤3B models only, Astra then budgets the prompt against this smaller effective window instead of g1nation.contextLength. Never applies to 4B+ models. Leave 0 unless you actually hit the issue — it reduces the output-token budget. Default: 0 (disabled)"
|
||
},
|
||
"g1nation.autoContinueOnOutputLimit": {
|
||
"type": "boolean",
|
||
"default": true,
|
||
"description": "When a reply is cut off because it hit the output-token limit, Astra continues it internally (compressed request — original question + the answer so far, not the whole context again) and shows one merged answer, instead of asking you to say \"이어서 작성해줘\". Default: true"
|
||
},
|
||
"g1nation.maxAutoContinuations": {
|
||
"type": "number",
|
||
"default": 4,
|
||
"minimum": 0,
|
||
"maximum": 10,
|
||
"description": "Maximum number of automatic continuation rounds per reply (prevents runaway loops). Raise it (e.g. 5–6) for long-form answers on slow local models; set 0 to disable auto-continuation. Default: 4"
|
||
},
|
||
"g1nation.finalOnlyRetryOnThoughtLeak": {
|
||
"type": "boolean",
|
||
"default": true,
|
||
"description": "If the model emits only hidden reasoning (<think>, <|channel|>thought, \"Thinking Process:\" …) and no user-visible answer, Astra silently re-asks it for the final answer only. Hidden reasoning is never shown either way. Default: true"
|
||
},
|
||
"g1nation.lmStudio.idleTimeoutMs": {
|
||
"type": "number",
|
||
"default": 300000,
|
||
"minimum": 0,
|
||
"description": "Auto-eject the loaded LM Studio model after this many milliseconds of inactivity. Set to 0 to disable. Default: 300000 (5 minutes)."
|
||
},
|
||
"g1nation.lmStudio.autoLoadOnSelect": {
|
||
"type": "boolean",
|
||
"default": true,
|
||
"description": "Automatically load LM Studio models into memory when selected from the Astra sidebar."
|
||
},
|
||
"g1nation.lmStudio.sampling.topP": {
|
||
"type": "number",
|
||
"default": 0.9,
|
||
"minimum": 0,
|
||
"maximum": 1,
|
||
"description": "Nucleus sampling cutoff. Small / quantized models often spew wrong-neighbour tokens (한글 깨짐: 붕괴→붕점) when the tail is wide. Lower (0.8–0.9) tightens; 1.0 disables. Applied to both SDK and REST paths."
|
||
},
|
||
"g1nation.lmStudio.sampling.topK": {
|
||
"type": "number",
|
||
"default": 20,
|
||
"minimum": 0,
|
||
"description": "Top-K sampling cutoff. 0 disables. Default 20 — tighter for small models, raise to 40–80 for large models that already sample well."
|
||
},
|
||
"g1nation.lmStudio.sampling.minP": {
|
||
"type": "number",
|
||
"default": 0.05,
|
||
"minimum": 0,
|
||
"maximum": 1,
|
||
"description": "Min-P floor — discards tokens with probability below this fraction of the top token. Good defence against rare-token glitches. 0 disables."
|
||
},
|
||
"g1nation.lmStudio.sampling.repeatPenalty": {
|
||
"type": "number",
|
||
"default": 1.1,
|
||
"minimum": 1,
|
||
"maximum": 2,
|
||
"description": "Repeat / frequency penalty to curb stutter (것입니다서입니다…). 1.0 disables. Values 1.05–1.2 are typical."
|
||
},
|
||
"g1nation.lmStudio.statsInBudget": {
|
||
"type": "boolean",
|
||
"default": true,
|
||
"description": "Show token/s and time-to-first-token from LM Studio prediction stats in the context-budget badge after each turn (SDK path only)."
|
||
},
|
||
"g1nation.lmStudio.draftModel": {
|
||
"type": "string",
|
||
"default": "",
|
||
"description": "[Speculative decoding] LM Studio model key of a small draft model (e.g. 'gemma-2b-it') used to accelerate the main model. Empty disables. 1.5–3x throughput on large models. The draft must be downloaded in LM Studio (load is automatic on first use)."
|
||
},
|
||
"g1nation.lmStudio.load.flashAttention": {
|
||
"type": "boolean",
|
||
"default": true,
|
||
"description": "[Load option] Enable Flash Attention when loading models. Faster generation + lower memory on compatible hardware, especially helpful for long contexts. Default: true."
|
||
},
|
||
"g1nation.lmStudio.load.gpuOffloadRatio": {
|
||
"type": "string",
|
||
"default": "max",
|
||
"description": "[Load option] How much of the model to offload to GPU. 'max' = all (default), 'off' = CPU only, or a number 0–1 (e.g. '0.5' = half). Numeric strings are parsed."
|
||
},
|
||
"g1nation.lmStudio.load.offloadKVCacheToGpu": {
|
||
"type": "boolean",
|
||
"default": true,
|
||
"description": "[Load option] Keep KV cache on GPU memory. Faster but requires VRAM headroom. Default: true."
|
||
},
|
||
"g1nation.lmStudio.load.keepModelInMemory": {
|
||
"type": "boolean",
|
||
"default": true,
|
||
"description": "[Load option] Prevent the model from being swapped out of system memory. Improves interactive responsiveness; raises RAM use. Default: true."
|
||
},
|
||
"g1nation.lmStudio.load.useFp16ForKVCache": {
|
||
"type": "boolean",
|
||
"default": false,
|
||
"description": "[Load option] Store KV cache in FP16 (halves cache memory). Tiny quality impact for most models — try if you run out of VRAM at long contexts. Default: false."
|
||
},
|
||
"g1nation.lmStudio.load.evalBatchSize": {
|
||
"type": "number",
|
||
"default": 0,
|
||
"minimum": 0,
|
||
"description": "[Load option] Token batch size during evaluation. 0 = engine default. Higher (512–1024) improves prefill speed on GPU at the cost of memory."
|
||
},
|
||
"g1nation.localBrainPath": {
|
||
"type": "string",
|
||
"default": "",
|
||
"description": "Folder path for your local Second Brain knowledge base. Leave empty to use the default folder."
|
||
},
|
||
"g1nation.brainProfiles": {
|
||
"type": "array",
|
||
"default": [],
|
||
"items": {
|
||
"type": "object",
|
||
"properties": {
|
||
"id": {
|
||
"type": "string",
|
||
"description": "Stable brain profile id."
|
||
},
|
||
"name": {
|
||
"type": "string",
|
||
"description": "Display name shown in the Astra brain selector."
|
||
},
|
||
"localBrainPath": {
|
||
"type": "string",
|
||
"description": "Local folder path used as this brain's markdown knowledge base."
|
||
},
|
||
"secondBrainRepo": {
|
||
"type": "string",
|
||
"description": "Optional Git repository URL for this brain."
|
||
},
|
||
"description": {
|
||
"type": "string",
|
||
"description": "Short note shown under the active brain status."
|
||
}
|
||
}
|
||
},
|
||
"description": "Multiple brain profiles. Each item supports id, name, localBrainPath, secondBrainRepo, and description."
|
||
},
|
||
"g1nation.activeBrainId": {
|
||
"type": "string",
|
||
"default": "",
|
||
"description": "Active brain profile id used for the current chat context."
|
||
},
|
||
"g1nation.secondBrainRepo": {
|
||
"type": "string",
|
||
"default": "",
|
||
"description": "Optional GitHub repository URL used for Second Brain sync."
|
||
},
|
||
"g1nation.autoPushBrain": {
|
||
"type": "boolean",
|
||
"default": false,
|
||
"description": "Automatically commit and push Second Brain changes after updates."
|
||
},
|
||
"g1nation.maxContextSize": {
|
||
"type": "number",
|
||
"default": 32000,
|
||
"description": "Maximum character count for active file context. Default: 32000"
|
||
},
|
||
"g1nation.maxAutoSteps": {
|
||
"type": "number",
|
||
"default": 50,
|
||
"description": "Maximum autonomous steps the agent can take per request. Default: 50"
|
||
},
|
||
"g1nation.dryRun": {
|
||
"type": "boolean",
|
||
"default": false,
|
||
"description": "If enabled, the agent will ask for approval before committing any file changes."
|
||
},
|
||
"g1nation.telegram.enabled": {
|
||
"type": "boolean",
|
||
"default": false,
|
||
"description": "Enable the Telegram bot integration. When on, Astra polls a bot you configure and replies to incoming messages. Off by default — Astra remains 100% local until you opt in."
|
||
},
|
||
"g1nation.telegram.allowedChatIds": {
|
||
"type": "array",
|
||
"default": [],
|
||
"items": {
|
||
"type": "number"
|
||
},
|
||
"description": "Optional allowlist of Telegram chat IDs that may message the bot. When empty, every chat that messages the bot is accepted (use with caution)."
|
||
},
|
||
"g1nation.telegram.defaultAgent": {
|
||
"type": "string",
|
||
"default": "",
|
||
"description": "Agent name (matches an entry in the Agent ↔ Knowledge map) used to scope Second Brain retrieval for Telegram replies. Empty falls back to the map's defaultAgent, then to whole-brain search."
|
||
},
|
||
"g1nation.telegram.agentByChatId": {
|
||
"type": "object",
|
||
"default": {},
|
||
"additionalProperties": {
|
||
"type": "string"
|
||
},
|
||
"description": "Per-chat override of the Telegram agent. Keys are stringified chat IDs, values are agent names from the knowledge map. Overrides telegram.defaultAgent for the listed chats."
|
||
},
|
||
"g1nation.telegram.contextChunks": {
|
||
"type": "number",
|
||
"default": 6,
|
||
"minimum": 0,
|
||
"maximum": 20,
|
||
"description": "How many Second Brain excerpts to inject into Telegram replies. Set 0 to disable RAG (plain prompt only)."
|
||
},
|
||
"g1nation.skillKnowledgeMapPath": {
|
||
"type": "string",
|
||
"default": "",
|
||
"description": "Absolute path to the agent ↔ knowledge mapping JSON. When empty, defaults to '<workspace>/.astra/agent-knowledge-map.json'."
|
||
},
|
||
"g1nation.skillKnowledgeMap": {
|
||
"type": "object",
|
||
"default": {},
|
||
"description": "Inline fallback for the agent ↔ knowledge mapping. Used only when the JSON file is missing. Shape: { defaultAgent?, agents: [{ name, knowledgeFolders, model?, description? }] }. Folder paths can be absolute, ~-prefixed, or relative to the active brain root."
|
||
},
|
||
"g1nation.agentSkillsPath": {
|
||
"type": "string",
|
||
"default": "",
|
||
"description": "Absolute path to the agent skills folder (`.agent/skills/*.md`). When empty, defaults to '<workspace>/.agent/skills'. Use this on Windows or when your skills live outside the workspace."
|
||
},
|
||
"g1nation.embeddingModel": {
|
||
"type": "string",
|
||
"default": "",
|
||
"description": "Embedding model registered in LM Studio / Ollama (e.g. 'text-embedding-bge-small-en-v1.5', 'nomic-embed-text', 'multilingual-e5-small'). When empty, Astra uses TF-IDF only. When set, the brain is embedded lazily in the background and retrieval blends TF-IDF + cosine similarity for synonym / paraphrase matching. Multilingual models are recommended for Korean content."
|
||
},
|
||
"g1nation.embeddingBlendAlpha": {
|
||
"type": "number",
|
||
"default": 0.5,
|
||
"minimum": 0,
|
||
"maximum": 1,
|
||
"description": "Hybrid score blend: 0 = pure TF-IDF (sparse / keyword), 1 = pure embedding cosine (dense / semantic), 0.5 = balanced. Only used when g1nation.embeddingModel is set. Default 0.5."
|
||
},
|
||
"g1nation.knowledgeMix.secondBrainWeight": {
|
||
"type": "number",
|
||
"default": 50,
|
||
"minimum": 0,
|
||
"maximum": 100,
|
||
"description": "Knowledge Mix (0–100): how heavily the assistant should lean on Second Brain evidence vs. its own general knowledge. 0 = Second Brain disabled (model knowledge only). 50 = balanced (legacy default). 100 = Second Brain is the primary evidence; model knowledge only fills harmless background. Per-agent overrides in the Agent Mapping panel win over this global value."
|
||
},
|
||
"g1nation.workflow.multiAgentMode": {
|
||
"type": "string",
|
||
"enum": ["auto", "always", "off"],
|
||
"default": "auto",
|
||
"markdownDescription": "Multi-Agent(5단계) 파이프라인 발동 모드.\n\n- `auto` (기본): 작은 모델(≤4B) 감지, 큰 prompt(컨텍스트의 30%+), 명시적 키워드(보고서/리뷰/심층 분석…), 또는 사용자가 `multiAgentEnabled`를 켰을 때 자동으로 발동. 짧은 인사·잡담은 제외.\n- `always`: 인사·잡담을 제외한 모든 요청에 5단계 파이프라인 사용. 작은 모델로도 답변이 한 번에 끝나지 않는다면 이 모드가 안정적.\n- `off`: 기존 키워드/길이 휴리스틱 + 수동 `multiAgentEnabled` 토글만 사용 (legacy 동작)."
|
||
},
|
||
"g1nation.workflow.autoCtxFractionThreshold": {
|
||
"type": "number",
|
||
"default": 0.30,
|
||
"minimum": 0.05,
|
||
"maximum": 0.95,
|
||
"markdownDescription": "`workflow.multiAgentMode = auto` 일 때, prompt 토큰이 효과적 context window 의 이 비율(0~1)을 넘으면 5단계 파이프라인을 강제 발동. 기본 0.30 — 작은 모델이 input으로 컨텍스트의 30% 이상을 먹기 시작하면 한 번에 답하려다 EOS/잘림이 잘 발생한다."
|
||
},
|
||
"g1nation.liveStreamTokens": {
|
||
"type": "boolean",
|
||
"default": true,
|
||
"markdownDescription": "모델 토큰을 받는 즉시 채팅 버블에 흘려보낼지 여부.\n\n- `true` (기본): 토큰을 받는 즉시 표시 → TTFT 체감 속도 향상. 생성이 끝나면 sanitize 된 최종 답변으로 `streamReplace` 가 한 번에 교체하므로 control token 노출은 잠깐만 가능.\n- `false`: 토큰을 내부에서만 누적, sanitize(`<|channel|>thought` / `<think>` / `Thinking Process:` 등 제거) 끝난 **최종 답변만 한 번에** 표시. 모델의 control token 이 잠깐이라도 화면에 노출되는 누설을 원천 차단."
|
||
},
|
||
"g1nation.outputFormat": {
|
||
"type": "string",
|
||
"enum": ["plain", "markdown"],
|
||
"default": "plain",
|
||
"markdownDescription": "최종 답변 표시 방식.\n\n- `plain` (기본): 모델이 무심코 내보낸 마크다운 마커(`##`, `**`, `__`, `> `, `* ` 등)를 후처리로 모두 제거. 섹션 라벨 텍스트(예: `핵심 요약`)는 유지되지만 헤더 마커는 사라져 깔끔한 plain text 로 보임. 작은 로컬 모델이 학습된 습관으로 `## 다음 한 수` 같은 마커를 흘리는 문제 차단.\n- `markdown`: legacy 동작. 모델 출력을 그대로 렌더러에 넘김."
|
||
},
|
||
"g1nation.chronicleAutoRecord": {
|
||
"type": "boolean",
|
||
"default": true,
|
||
"markdownDescription": "자동 기록 (Project Chronicle Auto-Record).\n\n- `true` (기본): 매 chat turn 후 의미 있는 대화(planning / decision / bug / development / discussion 유형 자동 판별)를 활성 프로젝트의 Chronicle 폴더에 자동 저장.\n- `false`: 자동 저장 OFF. 수동 기록 (도구 ▾ 의 기록 항목, `/wiki` 등) 은 계속 가능.\n\n사이드바 **도구 ▾** 메뉴의 `자동 기록` 토글로 즉시 전환 가능 — 설정 패널까지 들어갈 필요 없음."
|
||
},
|
||
"g1nation.company.intentClassifierModel": {
|
||
"type": "string",
|
||
"default": "",
|
||
"description": "Model used to classify whether an incoming chat message in 1인 기업 모드 is a (a) casual chat / question, (b) follow-up on the previous round, or (c) a brand-new task that should trigger the full work pipeline. Empty → uses g1nation.defaultModel. Pick a fast small model (e.g. gemma 4 e2b) so the classifier doesn't add latency before every chat send. The classifier runs once per user message and returns a one-token-ish JSON verdict, so even slow hardware sees minimal overhead."
|
||
},
|
||
"g1nation.company.disableIntentClassifier": {
|
||
"type": "boolean",
|
||
"default": false,
|
||
"description": "Bypass the intent classifier and always run the full work pipeline on every chat message in 1인 기업 모드 (legacy behaviour). Enable this only if you want every input — including 'thanks', 'show me X again' — to dispatch all agents. Off by default because most chat messages aren't new work and shouldn't burn a full pipeline."
|
||
},
|
||
"g1nation.company.autoSelectPipeline": {
|
||
"type": "boolean",
|
||
"default": true,
|
||
"description": "Let the intent classifier *automatically switch* to the pipeline it recommends for this turn (e.g. short '기획서까지만' for a planning ask, full '풀 프로덕트' for an end-to-end product). Your explicitly-activated pipeline is bypassed for the round but the activation itself isn't changed. On by default — the classifier's read of the user's intent (especially explicit signals like '기획만'·'디자인만') should be honoured. Set to false if you'd rather always run the pipeline you activated yourself."
|
||
},
|
||
"g1nation.company.intentAlignmentMode": {
|
||
"type": "string",
|
||
"enum": [
|
||
"off",
|
||
"smart",
|
||
"strict"
|
||
],
|
||
"default": "smart",
|
||
"description": "Intent Alignment — turn user prompts into an explicit Requirement Contract (C-G-C-F-Q) before dispatching a pipeline. 'off' = legacy, pipeline runs immediately. 'smart' (default) = run when confidence is high, else show a confirmation card; ask up to N rounds of clarifying questions if information is missing. 'strict' = always show the contract card and require user confirmation, regardless of confidence. Goal: stop agents from silently guessing at the user's mental model."
|
||
},
|
||
"g1nation.company.intentAlignmentMaxRounds": {
|
||
"type": "number",
|
||
"minimum": 1,
|
||
"maximum": 5,
|
||
"default": 3,
|
||
"description": "Maximum back-and-forth rounds the Intent Alignment analyzer is allowed to ask before forcing a 'confirm or cancel' card (it stops asking new questions and shows the current contract for user approval). Each round = one LLM call. Default 3."
|
||
},
|
||
"g1nation.selfReflector.enabled": {
|
||
"type": "boolean",
|
||
"default": false,
|
||
"description": "Self-Reflector Phase A — append a [Self-Reflector Check] block at the end of every substantive LLM answer (Consistency / Completeness / Accuracy, plus References / Paths for code answers). Zero extra LLM calls — the rule lives in the system prompt and the model self-imposes the checklist. OFF by default: the check block is an internal verification log that leaks into the user-facing answer and reads as unpolished. Enable only if you want that transparency block visible."
|
||
},
|
||
"g1nation.selfReflector.externalVerification": {
|
||
"type": "boolean",
|
||
"default": false,
|
||
"description": "Self-Reflector Phase B — after every 1인 기업 specialist response, run a *separate* LLM call to verify the output from an outside-context perspective (catches the 'same model self-validates' blind spot). Failed checks trigger one auto-revise round. Off by default — adds +1 LLM call per dispatched stage."
|
||
},
|
||
"g1nation.selfReflector.executionVerification": {
|
||
"type": "boolean",
|
||
"default": false,
|
||
"description": "Self-Reflector Phase C — after a code file is created via <create_file>, automatically run the language's syntax check (Python: py_compile, JS: node --check, TS: project tsc --noEmit). Failures are surfaced in the action report so the user (and the agent on a follow-up) can see exactly what broke. Requires the language toolchain installed on the user's machine. Off by default."
|
||
},
|
||
"g1nation.company.pixelOffice.enabled": {
|
||
"type": "boolean",
|
||
"default": true,
|
||
"description": "Show the Pixel Office visualisation panel above the chat — a small pixel-office-style display that mirrors the agent's current pipeline status (analyzing, need_clarification, executing, reviewing, waiting_approval, done, etc.) and the current task / contract / open questions. UI layer only; turning it off does not change any agent behaviour."
|
||
},
|
||
"g1nation.company.pixelOffice.bubbles": {
|
||
"type": "boolean",
|
||
"default": true,
|
||
"description": "Show short comic-style speech bubbles above the Pixel Office character on status changes / key events (e.g. '코드 들어간다', '잠깐, 이건 다시 보자', '좋아, 끝났다!'). Bubbles are purely narrative — they never influence the agent's decisions. Disable for a quieter UI."
|
||
},
|
||
"g1nation.google.clientId": {
|
||
"type": "string",
|
||
"default": "",
|
||
"scope": "machine",
|
||
"markdownDescription": "Google OAuth Client ID — `console.cloud.google.com/apis/credentials` → OAuth 2.0 Client ID (Desktop app) 생성 후 복사. **`Astra: Google Calendar OAuth 연결 (쓰기) 🔐`** 명령을 한 번 실행하면 이 값이 자동으로 채워집니다. Calendar + Sheets 둘 다 이 자격증명을 공유.\n\n_scope: machine — Settings Sync 로 다른 기기에 공유되지 않음._"
|
||
},
|
||
"g1nation.google.clientSecret": {
|
||
"type": "string",
|
||
"default": "",
|
||
"scope": "machine",
|
||
"markdownDescription": "Google OAuth Client Secret — Client ID 와 같은 페이지에서 발급. Desktop app OAuth 의 secret 은 Google 가이드상 *진짜 비밀이 아닌 식별자* 지만, settings.json 에 그대로 들어가므로 git 커밋 / 화면 공유 시 주의.\n\n_scope: machine — Settings Sync 안 됨._"
|
||
},
|
||
"g1nation.google.calendarId": {
|
||
"type": "string",
|
||
"default": "primary",
|
||
"markdownDescription": "일정을 등록할 Google Calendar 식별자. 기본 `primary` (본인 메인 캘린더). 특정 캘린더 쓰려면 Calendar 설정 → 캘린더 통합 → 'Calendar ID' 복사 (예: `xxxxxxx@group.calendar.google.com`)."
|
||
},
|
||
"g1nation.google.defaultEventDurationMinutes": {
|
||
"type": "number",
|
||
"default": 60,
|
||
"minimum": 5,
|
||
"maximum": 1440,
|
||
"description": "end / duration 둘 다 없는 일정의 기본 길이 (분). agent 가 회의록에서 시각만 추출하고 종료 시각은 명시 안 했을 때 적용."
|
||
},
|
||
"g1nation.google.icalUrl": {
|
||
"type": "string",
|
||
"default": "",
|
||
"scope": "machine",
|
||
"markdownDescription": "Google Calendar **비공개 iCal URL** — 읽기 전용 모드용. `calendar.google.com/calendar/u/0/r/settings` → 본인 캘린더 → '캘린더 통합' → '비공개 주소(iCal 형식)' 복사. **이 URL 을 가진 사람은 본인 캘린더 모든 일정을 볼 수 있으니 절대 공개 금지.**\n\n_scope: machine — Settings Sync 안 됨. OAuth 와는 별개 — 둘 다 셋업해도 되고 한 쪽만 해도 됨._"
|
||
},
|
||
"g1nation.google.icalDaysAhead": {
|
||
"type": "number",
|
||
"default": 14,
|
||
"minimum": 1,
|
||
"maximum": 90,
|
||
"description": "iCal 캐시에 포함할 다가오는 일정 기간 (일). default 14 = 2주치."
|
||
},
|
||
"g1nation.providers.openrouter.enabled": {
|
||
"type": "boolean",
|
||
"default": false,
|
||
"description": "OpenRouter cloud provider 활성화 — Claude/Gemini/GPT 등 100+ 모델을 OpenAI 호환 API 로 사용. API key 는 Astra Settings 패널에서 등록 (Secret Storage 사용, settings.json 비저장)."
|
||
},
|
||
"g1nation.providers.openrouter.defaultModel": {
|
||
"type": "string",
|
||
"default": "",
|
||
"description": "OpenRouter 의 기본 모델 (예: 'anthropic/claude-3.5-sonnet'). 모델 선택 시 'openrouter:<model>' 형식으로 사이드바 dropdown 에 표시."
|
||
},
|
||
"g1nation.providers.anthropic.enabled": {
|
||
"type": "boolean",
|
||
"default": false,
|
||
"description": "Anthropic Claude 직접 API 활성화. OpenRouter 보다 마진 적고 prompt caching 등 native 기능 사용 가능. API key 는 Secret Storage."
|
||
},
|
||
"g1nation.providers.anthropic.defaultModel": {
|
||
"type": "string",
|
||
"default": "claude-3-5-sonnet-20241022",
|
||
"description": "Anthropic 의 기본 모델. 예: 'claude-3-5-sonnet-20241022', 'claude-3-5-haiku-20241022'."
|
||
},
|
||
"g1nation.providers.gemini.enabled": {
|
||
"type": "boolean",
|
||
"default": false,
|
||
"description": "Google Gemini 직접 API 활성화. 1M context (gemini-1.5-pro), 무료 tier 등 native 기능 사용. API key 는 Secret Storage."
|
||
},
|
||
"g1nation.providers.gemini.defaultModel": {
|
||
"type": "string",
|
||
"default": "gemini-2.0-flash-exp",
|
||
"description": "Gemini 의 기본 모델. 예: 'gemini-2.0-flash-exp', 'gemini-1.5-pro', 'gemini-1.5-flash'."
|
||
},
|
||
"g1nation.devilAgent.enabled": {
|
||
"type": "boolean",
|
||
"default": false,
|
||
"markdownDescription": "**Devil's Advocate (도현) 활성화** — 매 답변 직후 별도 LLM 호출로 *비판적 sparring partner* 가 한 문단 반박. 사용자의 사고를 *수동적 수용 → 능동적 방어* 로 전환시키는 게 목표. Local LLM 동일 모델 재사용, ~10-15% 추가 비용."
|
||
}
|
||
}
|
||
}
|
||
},
|
||
"scripts": {
|
||
"vscode:prepublish": "npm run test && npm run compile",
|
||
"compile": "esbuild src/extension.ts --bundle --platform=node --external:vscode --outfile=out/extension.js",
|
||
"watch": "tsc -watch -p ./",
|
||
"test": "jest --no-cache --forceExit",
|
||
"test:engine": "jest tests/agentEngine.test.ts --verbose --no-cache",
|
||
"pretest": "npm run compile"
|
||
},
|
||
"devDependencies": {
|
||
"@types/jest": "^29.5.14",
|
||
"@types/node": "18.x",
|
||
"@types/vscode": "^1.80.0",
|
||
"@vercel/ncc": "^0.38.4",
|
||
"esbuild": "^0.28.0",
|
||
"jest": "^29.7.0",
|
||
"ts-jest": "^29.4.9",
|
||
"typescript": "^5.1.3"
|
||
},
|
||
"dependencies": {
|
||
"@lmstudio/sdk": "^1.5.0",
|
||
"pdf-parse": "^2.4.5"
|
||
}
|
||
}
|