Release v2.1.8: Company Agent roster overhaul and UI polish

2026-05-14 22:25:48 +09:00
parent ac0085ab53
commit 6b10d002fa
21 changed files with 674 additions and 331 deletions
@@ -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
@@ -1,6 +1,6 @@
 {
  "version": 1,
-  "generatedAt": "2026-05-13T17:43:53.948Z",
+  "generatedAt": "2026-05-14T13:24:53.652Z",
  "files": {
    "src/agent.ts": {
      "mtimeMs": 1778683690000,
@@ -58,6 +58,16 @@
        "src/lib/engine"
      ]
    },
+    "src/agents/reflectionPersister.ts": {
+      "mtimeMs": 1778763469000,
+      "size": 11986,
+      "lines": 308,
+      "role": "Reflection → Lesson persistence Take the Reflector agent's structured critique and persist any substantive findings as a lesson card in <brainDir>/lessons/auto-reflector/. The existing brain retrieval",
+      "imports": [
+        "src/utils",
+        "src/retrieval/lessonHelpers"
+      ]
+    },
    "src/bridge.ts": {
      "mtimeMs": 1778681774000,
      "size": 9705,
@@ -72,9 +82,9 @@
      ]
    },
    "src/config.ts": {
-      "mtimeMs": 1778690442000,
-      "size": 9619,
-      "lines": 216,
+      "mtimeMs": 1778763415000,
+      "size": 10185,
+      "lines": 224,
      "role": "",
      "imports": []
    },
@@ -312,23 +322,22 @@
      ]
    },
    "src/features/company/agents.ts": {
-      "mtimeMs": 1778680824000,
-      "size": 6684,
-      "lines": 136,
-      "role": "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",
+      "mtimeMs": 1778764697000,
+      "size": 11623,
+      "lines": 184,
+      "role": "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",
      "imports": [
        "src/features/company/types"
      ]
    },
    "src/features/company/ceoPlanner.ts": {
-      "mtimeMs": 1778681095000,
-      "size": 8406,
-      "lines": 219,
+      "mtimeMs": 1778762677000,
+      "size": 11307,
+      "lines": 266,
      "role": "CEO planner — turns a user prompt into a CompanyTaskPlan. Lifecycle of one planner call: 1. Build the planner system prompt (template + active-agent list). 2. Hit the AI service with the user prompt a",
      "imports": [
        "src/core/services",
        "src/utils",
-        "src/features/company/agents",
        "src/features/company/companyConfig",
        "src/features/company/promptAssets",
        "src/features/company/promptBuilder",
@@ -336,22 +345,22 @@
      ]
    },
    "src/features/company/ceoReporter.ts": {
-      "mtimeMs": 1778681122000,
-      "size": 4812,
-      "lines": 120,
+      "mtimeMs": 1778762677000,
+      "size": 4895,
+      "lines": 122,
      "role": "CEO synthesis pass — runs after all specialists have finished. Given the per-agent outputs, this asks the CEO model to produce the final markdown report (✅ 완료 / 🚀 다음 / 💡 인사이트) that the user actually",
      "imports": [
        "src/core/services",
        "src/utils",
-        "src/features/company/agents",
+        "src/features/company/companyConfig",
        "src/features/company/promptAssets",
        "src/features/company/types"
      ]
    },
    "src/features/company/companyConfig.ts": {
-      "mtimeMs": 1778686762000,
-      "size": 13473,
-      "lines": 330,
+      "mtimeMs": 1778764783000,
+      "size": 39070,
+      "lines": 877,
      "role": "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",
      "imports": [
        "src/features/company/agents",
@@ -359,9 +368,9 @@
      ]
    },
    "src/features/company/dispatcher.ts": {
-      "mtimeMs": 1778686839000,
-      "size": 20029,
-      "lines": 434,
+      "mtimeMs": 1778762677000,
+      "size": 29279,
+      "lines": 631,
      "role": "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",
      "imports": [
        "src/core/services",
@@ -369,7 +378,6 @@
        "src/skills/scopedBrainRetriever",
        "src/skills/agentKnowledgeMap",
        "src/retrieval/knowledgeMix",
-        "src/features/company/agents",
        "src/features/company/companyConfig",
        "src/features/company/ceoPlanner",
        "src/features/company/ceoReporter",
@@ -380,18 +388,28 @@
      ]
    },
    "src/features/company/index.ts": {
-      "mtimeMs": 1778686769000,
-      "size": 1114,
-      "lines": 55,
+      "mtimeMs": 1778764795000,
+      "size": 1827,
+      "lines": 83,
      "role": "Public API for 1인 기업 모드. Consumers (sidebarProvider, chatHandlers, command handlers) import from this barrel so internal layout can move around without touching every call site.",
      "imports": [
        "src/features/company/agents",
        "src/features/company/companyConfig",
        "src/features/company/types",
+        "src/features/company/pipelineTemplates",
        "src/features/company/dispatcher",
        "src/features/company/sessionStore"
      ]
    },
+    "src/features/company/pipelineTemplates.ts": {
+      "mtimeMs": 1778762677000,
+      "size": 11351,
+      "lines": 211,
+      "role": "Built-in pipeline templates for 1인 기업 모드. These are blueprints, not data — they're surfaced in the manage panel's \"템플릿에서 추가\" dropdown so a non-developer user can stamp out a working pipeline in one cl",
+      "imports": [
+        "src/features/company/types"
+      ]
+    },
    "src/features/company/promptAssets.ts": {
      "mtimeMs": 1778680887000,
      "size": 6782,
@@ -400,9 +418,9 @@
      "imports": []
    },
    "src/features/company/promptBuilder.ts": {
-      "mtimeMs": 1778686868000,
-      "size": 10317,
-      "lines": 202,
+      "mtimeMs": 1778762677000,
+      "size": 12835,
+      "lines": 231,
      "role": "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>, ",
      "imports": [
        "src/features/company/agents",
@@ -442,22 +460,22 @@
      ]
    },
    "src/features/company/telegramReport.ts": {
-      "mtimeMs": 1778686162000,
-      "size": 8111,
+      "mtimeMs": 1778762677000,
+      "size": 8126,
      "lines": 168,
      "role": "Telegram mirror for the secretary agent (영숙). After every company turn finishes, this helper takes the CEO synthesis + task list and pushes it to the user's Telegram chat — same behaviour as Connector",
      "imports": [
        "src/utils",
        "src/integrations/telegram/telegramClient",
        "src/integrations/telegram/conversationHistory",
-        "src/features/company/agents",
+        "src/features/company/companyConfig",
        "src/features/company/types"
      ]
    },
    "src/features/company/types.ts": {
-      "mtimeMs": 1778686714000,
-      "size": 6454,
-      "lines": 150,
+      "mtimeMs": 1778764725000,
+      "size": 14306,
+      "lines": 331,
      "role": "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",
      "imports": []
    },
@@ -629,9 +647,9 @@
      ]
    },
    "src/lib/engine.ts": {
-      "mtimeMs": 1778690608000,
-      "size": 40830,
-      "lines": 880,
+      "mtimeMs": 1778763448000,
+      "size": 42698,
+      "lines": 906,
      "role": "",
      "imports": [
        "src/core/lock",
@@ -639,7 +657,9 @@
        "src/utils",
        "src/lib/diagnostics",
        "src/lib/formatter",
-        "src/types/interfaces"
+        "src/types/interfaces",
+        "src/config",
+        "src/agents/reflectionPersister"
      ]
    },
    "src/lib/formatter.ts": {
@@ -902,9 +922,9 @@
      ]
    },
    "src/sidebar/chatHandlers.ts": {
-      "mtimeMs": 1778686906000,
-      "size": 13454,
-      "lines": 266,
+      "mtimeMs": 1778764814000,
+      "size": 22151,
+      "lines": 428,
      "role": "",
      "imports": [
        "src/sidebarProvider",
@@ -923,9 +943,9 @@
      ]
    },
    "src/sidebarProvider.ts": {
-      "mtimeMs": 1778693581000,
-      "size": 132228,
-      "lines": 3026,
+      "mtimeMs": 1778764853000,
+      "size": 141684,
+      "lines": 3232,
      "role": "",
      "imports": [
        "src/utils",
@@ -945,7 +965,8 @@
        "src/features/projectArchitecture",
        "src/features/projectArchitecture/intentDetector",
        "src/features/company",
-        "src/core/services"
+        "src/core/services",
+        "src/features/company/dispatcher"
      ]
    },
    "src/skills/agentKnowledgeMap.ts": {
@@ -1021,8 +1042,8 @@
      "imports": []
    },
    "media/settings-panel.html": {
-      "mtimeMs": 1778255979000,
-      "size": 7659,
+      "mtimeMs": 1778763966000,
+      "size": 7678,
      "lines": 164,
      "role": "Astra Settings",
      "imports": []
@@ -1035,23 +1056,23 @@
      "imports": []
    },
    "media/sidebar.css": {
-      "mtimeMs": 1778688155000,
-      "size": 49347,
-      "lines": 1225,
+      "mtimeMs": 1778764979000,
+      "size": 59761,
+      "lines": 1450,
      "role": "Stylesheet",
      "imports": []
    },
    "media/sidebar.html": {
-      "mtimeMs": 1778687548000,
-      "size": 20499,
-      "lines": 356,
+      "mtimeMs": 1778764039000,
+      "size": 28185,
+      "lines": 452,
      "role": "Astra",
      "imports": []
    },
    "media/sidebar.js": {
-      "mtimeMs": 1778688191000,
-      "size": 103898,
-      "lines": 1874,
+      "mtimeMs": 1778764936000,
+      "size": 158341,
+      "lines": 2791,
      "role": "",
      "imports": []
    },
@@ -1507,8 +1528,29 @@
      "role": "Bug: 문제점을 읽고 어떻게 개선하는게 최선인지 분석해주면 좋겠어. 알겠습니다. 지금부터 ConnectAI 프로젝트에만 완전히 집중하겠습니다. ...",
      "imports": []
    },
+    "docs/records/ConnectAI/bugs/BUG-0012-질문이-있어-논문을-쓰려고해-논문-주제는-서비스적이-아닌-사용자가-ai에게-구조로-질문을-해야-사용자의-의도.md": {
+      "mtimeMs": 1778762677000,
+      "size": 2354,
+      "lines": 16,
+      "role": "Bug: 질문이 있어. 논문을 쓰려고해. 논문 주제는 서비스적이 아닌 사용자가 ai에게 구조로 질문을 해야 사용자의 의도에 맞는 답변을 받을 수 있을까야...",
+      "imports": []
+    },
+    "docs/records/ConnectAI/bugs/BUG-0013-thesis-paper를-쓰려고-하는데-아래와-같이-쓰면-좋을까-이런-식으로-쓰면-되지-않을까-싶음-1-in.md": {
+      "mtimeMs": 1778762677000,
+      "size": 2527,
+      "lines": 16,
+      "role": "Bug: Thesis paper를 쓰려고 하는데 아래와 같이 쓰면 좋을까? 이런 식으로 쓰면 되지 않을까 싶음 1. Introduction Thesis ...",
+      "imports": []
+    },
+    "docs/records/ConnectAI/bugs/BUG-0014-논문-outline-title-인간-ai-상호작용에서-의도-정렬을-높이기-위한-최소-질의-구조-연구-또는-사.md": {
+      "mtimeMs": 1778762677000,
+      "size": 2531,
+      "lines": 16,
+      "role": "Bug: 논문 Outline Title 인간-AI 상호작용에서 의도 정렬을 높이기 위한 최소 질의 구조 연구 또는 사용자의 인지적 편향을 보완하는 구조화...",
+      "imports": []
+    },
    "docs/records/ConnectAI/chronicle.config.json": {
-      "mtimeMs": 1778694061000,
+      "mtimeMs": 1778763875000,
      "size": 416,
      "lines": 11,
      "role": "JSON configuration",
@@ -1584,6 +1626,20 @@
      "role": "ADR: /Volumes/Data/project/Antigravity/ConnectAI self reflection 기능이 적용되었는지 확인해줘. 1인 ...",
      "imports": []
    },
+    "docs/records/ConnectAI/decisions/ADR-0011-e-wiki-connectai-self-reflection-기능이-있는데-어떻게-self-reflection.md": {
+      "mtimeMs": 1778762677000,
+      "size": 1604,
+      "lines": 19,
+      "role": "ADR: E:\\Wiki\\connectai self reflection 기능이 있는데 어떻게 SELF REFLECTION이 반영되는지 분석해줘.",
+      "imports": []
+    },
+    "docs/records/ConnectAI/decisions/ADR-0012-e-wiki-connectai-self-reflection-기능이-있는데-어떻게-self-reflection.md": {
+      "mtimeMs": 1778762677000,
+      "size": 1448,
+      "lines": 19,
+      "role": "ADR: E:\\Wiki\\connectai self reflection 기능이 있는데 어떻게 SELF REFLECTION이 반영되는지 분석해줘.",
+      "imports": []
+    },
    "docs/records/ConnectAI/development/2026-05-02_answer-format-readability-tuning.md": {
      "mtimeMs": 1777808065000,
      "size": 1534,
@@ -1724,6 +1780,13 @@
      "role": "Development Log: 너는 분석 요청하거나 내가 작업 요청을 할때 connectai architecture.md 문서를 참고하고 작업을 하나?",
      "imports": []
    },
+    "docs/records/ConnectAI/development/2026-05-14_reflector-에이전트가-1인-기업-에이전트-목록에는-안보이는데_implementation.md": {
+      "mtimeMs": 1778762677000,
+      "size": 1519,
+      "lines": 24,
+      "role": "Development Log: REFLECTOR 에이전트가 1인 기업 에이전트 목록에는 안보이는데",
+      "imports": []
+    },
    "docs/records/ConnectAI/discussions/2026-05-13_volumes-data-project-antigravity-connectai-이-프로젝트-작업-할-거야.md": {
      "mtimeMs": 1778690673000,
      "size": 652,
@@ -1752,6 +1815,13 @@
      "role": "Discussion: /Volumes/Data/project/Antigravity/ConnectAI 이 프로젝트를 작업할거야.",
      "imports": []
    },
+    "docs/records/ConnectAI/discussions/2026-05-14_최성연-알아-칼리버스에서-근무한데.md": {
+      "mtimeMs": 1778762677000,
+      "size": 1297,
+      "lines": 16,
+      "role": "Discussion: 최성연 알아? 칼리버스에서 근무한데",
+      "imports": []
+    },
    "docs/records/ConnectAI/planning/2026-05-02_project-chronicle-guard.md": {
      "mtimeMs": 1777808065000,
      "size": 2946,
@@ -1795,7 +1865,7 @@
      "imports": []
    },
    "docs/records/ConnectAI/timeline.md": {
-      "mtimeMs": 1778694061000,
+      "mtimeMs": 1778763539000,
      "size": 8783,
      "lines": 134,
      "role": "Project Timeline",