Release v2.1.8: Company Agent roster overhaul and UI polish
This commit is contained in:
g1nation
@@ -3,15 +3,15 @@
|
||||
<!-- ASTRA:AUTO-START -->
|
||||
|
||||
## Snapshot
|
||||
- **Workspace**: `ConnectAI` `v2.1.2` _(absolute path varies by environment; resolved from the active VS Code workspace)_
|
||||
- **Workspace**: `ConnectAI` `v2.1.8` _(absolute path varies by environment; resolved from the active VS Code workspace)_
|
||||
- **Description**: The personal intelligence layer for Antigravity and VS Code. A private cognitive partner for deep project context, memory, and proactive strategic decision-making.
|
||||
- **Stack**: TypeScript, Node.js, VS Code Extension, LM Studio SDK, Test runner
|
||||
- **Stats**: 205 source files, ~36,036 lines across 5 top-level modules.
|
||||
- **Stats**: 214 source files, ~39,400 lines across 5 top-level modules.
|
||||
|
||||
## Last Refresh
|
||||
- **Time**: 2026-05-13T17:43:53.933Z
|
||||
- **Files newly analysed**: 0
|
||||
- **Files reused from cache**: 205
|
||||
- **Time**: 2026-05-14T13:24:53.642Z
|
||||
- **Files newly analysed**: 11
|
||||
- **Files reused from cache**: 203
|
||||
|
||||
## Directory Map
|
||||
```mermaid
|
||||
@@ -37,11 +37,11 @@ mindmap
|
||||
> Arrows: which top-level module imports from which.
|
||||
```mermaid
|
||||
flowchart LR
|
||||
src["src/<br/>100 files"]
|
||||
src["src/<br/>102 files"]
|
||||
media["media/<br/>6 files"]
|
||||
tests["tests/<br/>27 files"]
|
||||
core_py["core_py/<br/>6 files"]
|
||||
docs["docs/<br/>66 files"]
|
||||
docs["docs/<br/>73 files"]
|
||||
tests --> src
|
||||
```
|
||||
|
||||
@@ -53,21 +53,21 @@ flowchart LR
|
||||
|
||||
## Hub Files
|
||||
> Imported by many other files — touching these has wide blast radius.
|
||||
- `src/utils.ts` — referenced by **43** files
|
||||
- `src/config.ts` — referenced by **12** files
|
||||
- `src/utils.ts` — referenced by **44** files
|
||||
- `src/config.ts` — referenced by **13** files
|
||||
- `src/lib/paths.ts` — referenced by **10** files
|
||||
- `src/features/company/types.ts` — referenced by **9** files · Type definitions for the 1인 기업 (One-Person Company) mode. The mode turns the user into a virtual CEO that dispatches work to a roster of specialist agents. Each turn produces a session directory conta
|
||||
- `src/features/company/agents.ts` — referenced by **7** files · The 9-agent roster for 1인 기업 모드. Each entry is a static description — persona, role, specialty — used to build the specialist's system prompt at dispatch time. The set was adopted from Connectorigin's
|
||||
- `src/features/company/types.ts` — referenced by **10** files · Type definitions for the 1인 기업 (One-Person Company) mode. The mode turns the user into a virtual CEO that dispatches work to a roster of specialist agents. Each turn produces a session directory conta
|
||||
- `src/retrieval/lessonHelpers.ts` — referenced by **6** files · Lesson / Experience Memory — pure helpers (no vscode dependency) "Lesson" = a markdown file in the active brain that captures a past mistake/risk and how to avoid repeating it. Identified by a lessons
|
||||
- `src/skills/agentKnowledgeMap.ts` — referenced by **6** files
|
||||
- `src/lib/engine.ts` — referenced by **6** files
|
||||
- `src/core/services.ts` — referenced by **6** files
|
||||
|
||||
## Modules
|
||||
|
||||
### `src/` — 100 files, ~23,874 lines
|
||||
### `src/` — 102 files, ~25,874 lines
|
||||
|
||||
**Sub-directories**
|
||||
- `src/features/` (28) — The 9-agent roster for 1인 기업 모드. Each entry is a static description — persona, role, specialty — used to build the speci
|
||||
- `src/features/` (29) — 기본 에이전트 로스터 — 1인 기업 모드의 출고 디폴트. 설계 의도: 제품 개발 파이프라인(기획 → 디자인 → 개발 → QA → 출시 → 마케팅 → 회고)을 한 사람이 1인 기업으로 운영할 때 필요한 직군을 모두 커
|
||||
- `src/core/` (15) — Astra Path Resolver (경로 해결기) Astra의 모든 데이터 파일(.astra 디렉토리)의 경로를 중앙에서 관리합니다. 확장 프로그램의 설치 경로(extensionUri) 기반으로 .astra 디렉토
|
||||
- `src/memory/` (8) — Episodic Memory (일화 기억) 과거 대화/회의/결정의 맥락 흐름을 저장합니다. 세션 종료 시 자동으로 에피소드를 요약하여 저장합니다. "왜 이렇게 결정했는지", "어떤 흐름으로 진행했는지" 기록. 저장
|
||||
- `src/retrieval/` (8) — Brain Index — persistent, mtime-keyed tokenized cache of the Second Brain RAG 검색은 매 질의마다 브레인의 모든 .md 파일을 읽고 토크나이즈해서 TF-I
|
||||
@@ -77,42 +77,42 @@ flowchart LR
|
||||
- `src/lmstudio/` (4) — 4 files (.ts)
|
||||
- `src/sidebar/` (4) — 4 files (.ts)
|
||||
- `src/skills/` (4) — 4 files (.ts)
|
||||
- `src/agents/` (2) — 2 files (.ts)
|
||||
- `src/agents/` (3) — Reflection → Lesson persistence Take the Reflector agent's structured critique and persist any substantive findings as a
|
||||
- `src/scaffolder/` (2) — Scaffolder template catalog. Templates are pure data — (projectName) => { [relativePath]: contents }. New templates are
|
||||
|
||||
**Key files**
|
||||
- `src/utils.ts` (268 lines)
|
||||
- `src/config.ts` (216 lines)
|
||||
- `src/features/company/types.ts` (150 lines) — Type definitions for the 1인 기업 (One-Person Company) mode. The mode turns the user into a virtual CEO that dispatches work to a roster of specialist agents. Each turn produces a session directory conta
|
||||
- `src/config.ts` (224 lines)
|
||||
- `src/features/company/types.ts` (331 lines) — Type definitions for the 1인 기업 (One-Person Company) mode. The mode turns the user into a virtual CEO that dispatches work to a roster of specialist agents. Each turn produces a session directory conta
|
||||
- `src/lib/paths.ts` (151 lines)
|
||||
- `src/sidebarProvider.ts` (3026 lines)
|
||||
- `src/features/company/agents.ts` (136 lines) — The 9-agent roster for 1인 기업 모드. Each entry is a static description — persona, role, specialty — used to build the specialist's system prompt at dispatch time. The set was adopted from Connectorigin's
|
||||
- `src/features/company/companyConfig.ts` (877 lines) — State + config plumbing for 1인 기업 모드. Two surfaces: - CompanyState (runtime data: enabled flag, company name, which agents are active, per-agent model overrides). Persisted in VS Code's globalState so
|
||||
- `src/sidebarProvider.ts` (3232 lines)
|
||||
- `src/memory/types.ts` (126 lines) — Memory Type Definitions (메모리 타입 정의) Astra의 5-Layer Cognitive Memory System의 모든 타입을 정의합니다. ① Short-Term ② Long-Term ③ Project ④ Procedural ⑤ Episodic
|
||||
- `src/retrieval/scoring.ts` (518 lines) — Scoring Engine — TF-IDF + Bilingual Tokenizer 단순 includes() 키워드 매칭을 넘어서, TF-IDF 가중치 기반의 문서 스코어링을 제공합니다. 한국어/영어 양국어 토크나이저를 포함합니다.
|
||||
- `src/skills/agentKnowledgeMap.ts` (374 lines)
|
||||
- `src/core/services.ts` (164 lines)
|
||||
- `src/agent.ts` (3232 lines)
|
||||
- `src/features/company/companyConfig.ts` (330 lines) — State + config plumbing for 1인 기업 모드. Two surfaces: - CompanyState (runtime data: enabled flag, company name, which agents are active, per-agent model overrides). Persisted in VS Code's globalState so
|
||||
- `src/retrieval/lessonHelpers.ts` (325 lines) — Lesson / Experience Memory — pure helpers (no vscode dependency) "Lesson" = a markdown file in the active brain that captures a past mistake/risk and how to avoid repeating it. Identified by a lessons
|
||||
- `src/lib/engine.ts` (880 lines)
|
||||
- `src/agent.ts` (3232 lines)
|
||||
- `src/lib/engine.ts` (906 lines)
|
||||
- `src/features/approval/approvalQueue.ts` (129 lines)
|
||||
- `src/integrations/telegram/telegramClient.ts` (154 lines)
|
||||
- `src/features/company/dispatcher.ts` (631 lines) — Sequential dispatcher for 1인 기업 모드. Drives one company "turn": user prompt → CEO planner (JSON {brief, tasks}) → for each task in plan: dispatch one specialist (sequentially) - build specialist prompt
|
||||
- `src/features/projectArchitecture/scanner.ts` (644 lines) — Deep static analyser for the Project Architecture Context generator. Walks the project tree (skipping the usual nodemodules / out / dist noise), pulls the role of each interesting file from its leadin
|
||||
- `src/lib/contextManager.ts` (275 lines) — Context Manager (컨텍스트 한계 관리) "context length = 132k" 는 "답변을 132k 토큰까지 생성해도 된다" 가 아닙니다. 시스템 프롬프트 + 대화 기록 + 입력 문서 + 생성될 답변 + 여유분 ≤ context length 이 모듈은 요청을 보내기 전에 입력 토큰을 추정하고, - 동적으로 출력 상한(maxTokens)을 계
|
||||
- `src/features/company/agents.ts` (184 lines) — 기본 에이전트 로스터 — 1인 기업 모드의 출고 디폴트. 설계 의도: 제품 개발 파이프라인(기획 → 디자인 → 개발 → QA → 출시 → 마케팅 → 회고)을 한 사람이 1인 기업으로 운영할 때 필요한 직군을 모두 커버한다. 각 에이전트는 - name — 직군에 어울리는 한국식 닉네임 - role — 한국어 정식 직함 (어떤 일을 하는 사람인지) - tagl
|
||||
- `src/core/astraPath.ts` (50 lines) — Astra Path Resolver (경로 해결기) Astra의 모든 데이터 파일(.astra 디렉토리)의 경로를 중앙에서 관리합니다. 확장 프로그램의 설치 경로(extensionUri) 기반으로 .astra 디렉토리를 해결하여, 사용자 프로젝트 루트가 아닌 ConnectAI 패키지 내부에 데이터를 저장합니다. 이 모듈은 AAL(Astra Autonomou
|
||||
- `src/extension.ts` (966 lines)
|
||||
- `src/features/projectChronicle/types.ts` (118 lines)
|
||||
- `src/lmstudio/client.ts` (147 lines)
|
||||
- `src/retrieval/brainIndex.ts` (325 lines) — Brain Index — persistent, mtime-keyed tokenized cache of the Second Brain RAG 검색은 매 질의마다 브레인의 모든 .md 파일을 읽고 토크나이즈해서 TF-IDF 점수를 계산했습니다 — 파일 수가 많아지면 그게 병목입니다. 이 모듈은 <brainPath>/.astra/brain-index.json 에
|
||||
- `src/features/company/promptBuilder.ts` (202 lines) — System-prompt construction for company-mode agents. Each specialist needs a prompt that includes: - Their identity (name, role, specialty) + optional persona. - The action-tag contract (<createfile>,
|
||||
- `src/features/company/sessionStore.ts` (231 lines) — Disk persistence for company-mode session artefacts. Each company turn produces a timestamped directory: <workspaceRoot>/.astra/company/sessions/2026-05-13T21-29/ ├─ brief.md ← CEO's task decompositio
|
||||
- `src/features/company/promptBuilder.ts` (231 lines) — System-prompt construction for company-mode agents. Each specialist needs a prompt that includes: - Their identity (name, role, specialty) + optional persona. - The action-tag contract (<createfile>,
|
||||
|
||||
### `media/` — 6 files, ~4,099 lines
|
||||
### `media/` — 6 files, ~5,337 lines
|
||||
|
||||
**Key files**
|
||||
- `media/sidebar.css` (1225 lines) — Stylesheet
|
||||
- `media/sidebar.js` (1874 lines)
|
||||
- `media/sidebar.html` (356 lines) — Astra
|
||||
- `media/sidebar.css` (1450 lines) — Stylesheet
|
||||
- `media/sidebar.js` (2791 lines)
|
||||
- `media/sidebar.html` (452 lines) — Astra
|
||||
- `media/settings-panel.css` (210 lines) — Stylesheet
|
||||
- `media/settings-panel.html` (164 lines) — Astra Settings
|
||||
- `media/settings-panel.js` (270 lines)
|
||||
@@ -160,10 +160,10 @@ flowchart LR
|
||||
- `core_py/optimizer.py` (55 lines)
|
||||
- `core_py/queue_worker.py` (82 lines)
|
||||
|
||||
### `docs/` — 66 files, ~2,716 lines
|
||||
### `docs/` — 73 files, ~2,842 lines
|
||||
|
||||
**Sub-directories**
|
||||
- `docs/records/` (54) — Astra Project Chronicle Records
|
||||
- `docs/records/` (61) — Astra Project Chronicle Records
|
||||
- `docs/docs/` (5) — docs Chronicle Records
|
||||
|
||||
**Key files**
|
||||
@@ -220,7 +220,7 @@ flowchart LR
|
||||
- `g1nation.company.toggle` — Astra: Toggle 1인 기업 Mode
|
||||
- `g1nation.company.manage` — Astra: Manage 1인 기업 Agents
|
||||
- `g1nation.company.openSessions` — Astra: Open 1인 기업 Sessions Folder
|
||||
- **Configuration** (39 settings):
|
||||
- **Configuration** (40 settings):
|
||||
- `g1nation.multiAgentEnabled` *(boolean)* _(default: `false`)_ — Enable Multi-Agent Workflow (Planner -> Researcher -> Writer) for complex tasks.
|
||||
- `g1nation.memoryEnabled` *(boolean)* _(default: `true`)_ — Enable layered memory injection before each model response.
|
||||
- `g1nation.memoryShortTermMessages` *(number)* _(default: `8`)_ — Number of recent conversation messages included as short-term memory.
|
||||
@@ -260,6 +260,7 @@ flowchart LR
|
||||
- `g1nation.embeddingBlendAlpha` *(number)* _(default: `0.5`)_ — 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` *(number)* _(default: `50`)_ — 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). 1
|
||||
- `g1nation.enableReflection` *(boolean)* _(default: `true`)_ — Insert a Self-Reflection (Reflector) stage between Researcher and Writer in the multi-agent workflow. The Reflector critically reviews the plan and research output (gaps, contradictions, unsupported c
|
||||
- `g1nation.autoLessonFromReflection` *(boolean)* _(default: `true`)_ — Persist substantive Reflector critiques to the active brain as lesson cards under `lessons/auto-reflector/`. Future missions automatically retrieve these cards (via the existing Experience-Memory pipe
|
||||
|
||||
## Dependencies
|
||||
- **Runtime** (2): `@lmstudio/sdk`, `pdf-parse`
|
||||
@@ -307,7 +308,7 @@ Astra는 대표님의 명시적인 승인 하에 로컬 시스템의 강력한
|
||||
**Designed for High-Performance Decision Making.**
|
||||
Copyright (C) **g1nation**. All rights reserved.
|
||||
|
||||
_Last auto-scan: 2026-05-13T17:43:53.933Z · signature `5020e02c`_
|
||||
_Last auto-scan: 2026-05-14T13:24:53.642Z · signature `f554c52a`_
|
||||
<!-- ASTRA:AUTO-END -->
|
||||
|
||||
## Purpose
|
||||
|
||||
Reference in New Issue
Block a user