agestra 4.12.0 → 4.12.2

package/.claude-plugin/marketplace.json

@@ -12,7 +12,7 @@
       "name": "agestra",
       "source": "./",
       "description": "Orchestrate Ollama, Gemini, and Codex for multi-AI debates, code review, and cross-validation",
-      "version": "4.12.0",
+      "version": "4.12.2",
       "author": {
         "name": "mua-vtuber"
       },

package/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "agestra",
-  "version": "4.12.0",
+  "version": "4.12.2",
   "description": "Claude Code plugin — orchestrate Ollama, Gemini, and Codex for multi-AI debates, code review, and cross-validation",
   "mcpServers": {
     "agestra": {

package/.gemini/commands/agestra/design.toml

@@ -9,7 +9,7 @@ Use the shared workflow spec below as the source of truth and adapt it to the cu
 @{commands/design.md}
 
 Gemini-specific rules:
-- Start with `environment_check` and `provider_list`.
+- Start with `setup_status`, then `environment_check` and `provider_list`.
 - Prefer Agestra MCP tools, workspace documents, and debate flows over free-form brainstorming.
 - Translate Claude-specific wording into leader-host wording when Gemini is the active host.
 - Keep the final answer in the user's language.

package/README.ja.md

@@ -24,22 +24,37 @@ Claude では既存のプラグイン UX をそのまま維持します。Agestr
 
 ```
 npm run bundle
-npm run install:codex
+npm run install:codex:assets
 ```
 
-Codex ではリポジトリ直下の [AGENTS.md](AGENTS.md) と、登録済みの `agestra` MCP サーバーを一緒に使います。
+グローバル npm パッケージから使う場合:
+
+```
+npm install -g agestra
+agestra-install codex --assets
+```
+
+Codex ではリポジトリ直下の [AGENTS.md](AGENTS.md) と、登録済みの `agestra` MCP サーバーを一緒に使います。`--assets` は `.codex/agents/` に生成済み Codex custom agent もインストールし、Agestra host-asset manifest に記録します。MCP 登録だけでよい場合は `npm run install:codex` または `agestra-install codex` を使ってください。
 
 ### Gemini CLI
 
 ```
 npm run bundle
-npm run install:gemini
+npm run install:gemini:assets
 ```
 
-Gemini ではリポジトリ直下の [GEMINI.md](GEMINI.md) と、[`.gemini/commands/agestra/`](.gemini/commands/agestra) のプロジェクトコマンドを一緒に使います。
+グローバル npm パッケージから使う場合:
+
+```
+npm install -g agestra
+agestra-install gemini --assets --scope user
+```
+
+Gemini ではリポジトリ直下の [GEMINI.md](GEMINI.md) と、[`.gemini/commands/agestra/`](.gemini/commands/agestra) のプロジェクトコマンドを一緒に使います。user scope の `--assets` は Agestra Gemini native extension をインストールします。MCP 登録だけでよい場合は `npm run install:gemini` または `agestra-install gemini` を使ってください。
 
 セットアップ後に利用できる Gemini コマンド:
 
+- `/agestra:setup`
 - `/agestra:review`
 - `/agestra:design`
 - `/agestra:idea`
@@ -116,7 +131,7 @@ Gemini ではリポジトリ直下の [GEMINI.md](GEMINI.md) と、[`.gemini/com
 
 ## アーキテクチャ
 
-Turborepo モノレポで、9 パッケージ構成です:
+Turborepo モノレポで、8 パッケージ構成です:
 
 | パッケージ | 説明 |
 |------------|------|
@@ -329,8 +344,8 @@ agestra/
 │   └── bundle.js            # 単一ファイル MCP サーバーバンドル
 ├── scripts/
 │   ├── bundle.mjs           # esbuild バンドルスクリプト
-│   ├── install-host-mcp.mjs # Codex/Gemini に Agestra を登録
-│   └── uninstall-host-mcp.mjs # Codex/Gemini から Agestra 登録を削除
+│   ├── install-host-mcp.mjs # Claude/Codex/Gemini の MCP + host assets を登録
+│   └── uninstall-host-mcp.mjs # ホスト登録と管理対象 assets を削除
 ├── packages/
 │   ├── core/                # AIProvider、レジストリ、セキュリティ、ワーカー
 │   ├── provider-ollama/     # Ollama HTTP アダプター
@@ -363,14 +378,18 @@ Codex CLI:
 
 ```
 npm run uninstall:codex
+npm run uninstall:codex:assets
 ```
 
 Gemini CLI:
 
 ```
 npm run uninstall:gemini
+npm run uninstall:gemini:assets
 ```
 
+`*:assets` のアンインストールは、ホスト登録と未変更の生成済みホスト資産を一緒に削除します。ユーザーが生成済み資産を編集していた場合、Agestra はそのファイルを残して報告します。グローバル npm インストールでは `agestra-uninstall codex --assets` または `agestra-uninstall gemini --assets --scope user` を使ってください。
+
 生成済みのプロジェクトデータも削除したい場合は、`.agestra/` ディレクトリを手動で削除してください。
 
 ---

package/README.ko.md

@@ -26,23 +26,23 @@ Claude는 기존 플러그인 설치 UX를 그대로 유지합니다. Agestra가
 
 ```
 npm run bundle
-npm run install:codex
+npm run install:codex:assets
 ```
 
 전역 npm 패키지 기준:
 
 ```
 npm install -g agestra
-agestra-install codex
+agestra-install codex --assets
 ```
 
-저장소에서 작업 중이지만 등록 대상은 전역 npm 패키지로 하고 싶다면:
+저장소에서 작업 중이지만 전역 npm 패키지를 MCP만 등록하고 싶다면:
 
 ```
 npm run install:codex:global
 ```
 
-Codex는 저장소 루트의 [AGENTS.md](AGENTS.md)와 등록된 `agestra` MCP 서버를 함께 사용합니다.
+Codex는 저장소 루트의 [AGENTS.md](AGENTS.md)와 등록된 `agestra` MCP 서버를 함께 사용합니다. `--assets` 경로는 `.codex/agents/` 아래에 생성형 Codex custom agent도 설치하고 Agestra host-asset manifest에 기록합니다. MCP만 등록하려면 `npm run install:codex` 또는 `agestra-install codex`를 사용하세요.
 
 ### Gemini CLI
 
@@ -50,23 +50,23 @@ Codex는 저장소 루트의 [AGENTS.md](AGENTS.md)와 등록된 `agestra` MCP
 
 ```
 npm run bundle
-npm run install:gemini
+npm run install:gemini:assets
 ```
 
 전역 npm 패키지 기준:
 
 ```
 npm install -g agestra
-agestra-install gemini
+agestra-install gemini --assets --scope user
 ```
 
-저장소에서 작업 중이지만 등록 대상은 전역 npm 패키지로 하고 싶다면:
+저장소에서 작업 중이지만 전역 npm 패키지를 MCP만 등록하고 싶다면:
 
 ```
 npm run install:gemini:global
 ```
 
-Gemini는 저장소 루트의 [GEMINI.md](GEMINI.md)와 [`.gemini/commands/agestra/`](.gemini/commands/agestra) 프로젝트 커맨드를 함께 사용합니다.
+Gemini는 저장소 루트의 [GEMINI.md](GEMINI.md)와 [`.gemini/commands/agestra/`](.gemini/commands/agestra) 프로젝트 커맨드를 함께 사용합니다. user scope의 `--assets` 경로는 Agestra Gemini native extension을 설치합니다. MCP만 등록하려면 `npm run install:gemini` 또는 `agestra-install gemini`를 사용하세요.
 
 설치 후 Gemini에서 사용할 수 있는 명령:
 
@@ -158,7 +158,7 @@ winget install BurntSushi.ripgrep.MSVC
 
 ## 아키텍처
 
-Turborepo 모노레포, 9개 패키지:
+Turborepo 모노레포, 8개 패키지:
 
 | 패키지 | 설명 |
 |--------|------|
@@ -372,8 +372,8 @@ agestra/
 │   └── bundle.js            # 단일 파일 MCP 서버 번들
 ├── scripts/
 │   ├── bundle.mjs           # esbuild 번들 스크립트
-│   ├── install-host-mcp.mjs # Codex/Gemini에 Agestra 등록
-│   └── uninstall-host-mcp.mjs # Codex/Gemini에서 Agestra 제거
+│   ├── install-host-mcp.mjs # Claude/Codex/Gemini MCP + host assets 등록
+│   └── uninstall-host-mcp.mjs # 호스트 등록과 관리 자산 제거
 ├── packages/
 │   ├── core/                # AIProvider 인터페이스, 레지스트리, 보안, 워커
 │   ├── provider-ollama/     # Ollama HTTP 어댑터
@@ -406,14 +406,18 @@ Codex CLI:
 
 ```
 npm run uninstall:codex
+npm run uninstall:codex:assets
 ```
 
 Gemini CLI:
 
 ```
 npm run uninstall:gemini
+npm run uninstall:gemini:assets
 ```
 
+`*:assets` 제거 명령은 호스트 등록과 변경되지 않은 생성형 호스트 자산을 함께 제거합니다. 사용자가 생성된 자산을 수정했다면 Agestra는 삭제하지 않고 남겨둔 파일을 보고합니다. 전역 npm 설치에서는 `agestra-uninstall codex --assets` 또는 `agestra-uninstall gemini --assets --scope user`를 사용하세요.
+
 프로젝트에 생성된 데이터까지 지우려면 `.agestra/` 디렉터리를 수동으로 삭제하세요.
 
 ---

package/README.md

@@ -26,23 +26,23 @@ Repository checkout:
 
 ```
 npm run bundle
-npm run install:codex
+npm run install:codex:assets
 ```
 
 Global npm package:
 
 ```
 npm install -g agestra
-agestra-install codex
+agestra-install codex --assets
 ```
 
-If you want to register the global package while working from a repo checkout, use:
+If you want MCP-only registration of the global package while working from a repo checkout, use:
 
 ```
 npm run install:codex:global
 ```
 
-Codex uses the repository-level [AGENTS.md](AGENTS.md) instructions plus the registered `agestra` MCP server.
+Codex uses the repository-level [AGENTS.md](AGENTS.md) instructions plus the registered `agestra` MCP server. The `--assets` path also installs generated Codex custom agents under `.codex/agents/` and tracks them in the Agestra host-asset manifest. For MCP-only registration, use `npm run install:codex` or `agestra-install codex`.
 
 ### Gemini CLI
 
@@ -50,23 +50,23 @@ Repository checkout:
 
 ```
 npm run bundle
-npm run install:gemini
+npm run install:gemini:assets
 ```
 
 Global npm package:
 
 ```
 npm install -g agestra
-agestra-install gemini
+agestra-install gemini --assets --scope user
 ```
 
-If you want to register the global package while working from a repo checkout, use:
+If you want MCP-only registration of the global package while working from a repo checkout, use:
 
 ```
 npm run install:gemini:global
 ```
 
-Gemini uses the repository-level [GEMINI.md](GEMINI.md) context file plus project commands under [`.gemini/commands/agestra/`](.gemini/commands/agestra).
+Gemini uses the repository-level [GEMINI.md](GEMINI.md) context file plus project commands under [`.gemini/commands/agestra/`](.gemini/commands/agestra). The user-scope `--assets` path installs the Agestra Gemini native extension. For MCP-only registration, use `npm run install:gemini` or `agestra-install gemini`.
 
 Available Gemini commands after setup:
 
@@ -159,7 +159,7 @@ When external providers are available, text commands (review, design, idea) go d
 
 ## Architecture
 
-Turborepo monorepo with 9 packages:
+Turborepo monorepo with 8 packages:
 
 | Package | Description |
 |---------|-------------|
@@ -374,8 +374,8 @@ agestra/
 │   └── bundle.js            # Single-file MCP server bundle
 ├── scripts/
 │   ├── bundle.mjs           # esbuild bundle script
-│   ├── install-host-mcp.mjs # Register Agestra with Codex/Gemini
-│   └── uninstall-host-mcp.mjs # Remove Codex/Gemini MCP registration
+│   ├── install-host-mcp.mjs # Register Claude/Codex/Gemini MCP + host assets
+│   └── uninstall-host-mcp.mjs # Remove host registrations and managed assets
 ├── packages/
 │   ├── core/                # AIProvider interface, registry, security, workers
 │   ├── provider-ollama/     # Ollama HTTP adapter
@@ -408,14 +408,18 @@ Codex CLI:
 
 ```
 npm run uninstall:codex
+npm run uninstall:codex:assets
 ```
 
 Gemini CLI:
 
 ```
 npm run uninstall:gemini
+npm run uninstall:gemini:assets
 ```
 
+The `*:assets` uninstall commands remove both the host registration and unchanged generated host assets. If a generated asset was edited by the user, Agestra leaves it in place and reports it. For a global npm install, use `agestra-uninstall codex --assets` or `agestra-uninstall gemini --assets --scope user`.
+
 If you also want to delete generated project data, remove the `.agestra/` directory manually.
 
 ---

package/README.zh.md

@@ -24,22 +24,37 @@ Claude 保持现有插件安装体验不变。Agestra 会在首次使用时通
 
 ```
 npm run bundle
-npm run install:codex
+npm run install:codex:assets
 ```
 
-Codex 会结合仓库根目录下的 [AGENTS.md](AGENTS.md) 与已注册的 `agestra` MCP 服务一起工作。
+使用全局 npm 包时：
+
+```
+npm install -g agestra
+agestra-install codex --assets
+```
+
+Codex 会结合仓库根目录下的 [AGENTS.md](AGENTS.md) 与已注册的 `agestra` MCP 服务一起工作。`--assets` 还会在 `.codex/agents/` 下安装生成的 Codex custom agent，并写入 Agestra host-asset manifest。只注册 MCP 时，请使用 `npm run install:codex` 或 `agestra-install codex`。
 
 ### Gemini CLI
 
 ```
 npm run bundle
-npm run install:gemini
+npm run install:gemini:assets
 ```
 
-Gemini 会结合仓库根目录下的 [GEMINI.md](GEMINI.md) 与 [`.gemini/commands/agestra/`](.gemini/commands/agestra) 项目命令一起工作。
+使用全局 npm 包时：
+
+```
+npm install -g agestra
+agestra-install gemini --assets --scope user
+```
+
+Gemini 会结合仓库根目录下的 [GEMINI.md](GEMINI.md) 与 [`.gemini/commands/agestra/`](.gemini/commands/agestra) 项目命令一起工作。user scope 的 `--assets` 会安装 Agestra Gemini native extension。只注册 MCP 时，请使用 `npm run install:gemini` 或 `agestra-install gemini`。
 
 安装后可用的 Gemini 命令：
 
+- `/agestra:setup`
 - `/agestra:review`
 - `/agestra:design`
 - `/agestra:idea`
@@ -116,7 +131,7 @@ Gemini 会结合仓库根目录下的 [GEMINI.md](GEMINI.md) 与 [`.gemini/comma
 
 ## 架构
 
-这是一个包含 9 个包的 Turborepo monorepo：
+这是一个包含 8 个包的 Turborepo monorepo：
 
 | 包 | 说明 |
 |----|------|
@@ -329,8 +344,8 @@ agestra/
 │   └── bundle.js            # 单文件 MCP Server bundle
 ├── scripts/
 │   ├── bundle.mjs           # esbuild bundle 脚本
-│   ├── install-host-mcp.mjs # 为 Codex/Gemini 注册 Agestra
-│   └── uninstall-host-mcp.mjs # 从 Codex/Gemini 移除 Agestra 注册
+│   ├── install-host-mcp.mjs # 注册 Claude/Codex/Gemini MCP + host assets
+│   └── uninstall-host-mcp.mjs # 移除宿主注册和受管理资产
 ├── packages/
 │   ├── core/                # AIProvider 接口、注册表、安全、worker
 │   ├── provider-ollama/     # Ollama HTTP 适配器
@@ -363,14 +378,18 @@ Codex CLI：
 
 ```
 npm run uninstall:codex
+npm run uninstall:codex:assets
 ```
 
 Gemini CLI：
 
 ```
 npm run uninstall:gemini
+npm run uninstall:gemini:assets
 ```
 
+`*:assets` 卸载命令会同时移除宿主注册和未修改的生成宿主资产。如果用户编辑过生成资产，Agestra 会保留该文件并报告。使用全局 npm 安装时，请运行 `agestra-uninstall codex --assets` 或 `agestra-uninstall gemini --assets --scope user`。
+
 如果还想删除生成的项目数据，请手动删除 `.agestra/` 目录。
 
 ---

package/agents/agestra-team-lead.md

@@ -46,6 +46,10 @@ In autonomous mode, all phases still execute in order, but user approval gates a
 
 <Workflow>
 
+### Domain Dispatch
+
+If invoked with **Domain: design**, do not enter implementation decomposition, worker routing, or code-changing phases. Execute the structured consensus design workflow in `commands/design.md`, then report the resulting design artifacts.
+
 ### Phase 0: Clarity Gate
 
 If the user's request is vague (no file paths, no concrete acceptance criteria, ambiguous scope):

package/commands/design.md

@@ -9,12 +9,12 @@ You are executing the `/agestra design` command.
 
 ## Step 0: Setup preflight (MANDATORY)
 
-Before anything else, call `setup_status`. If it reports `Current config: not found`, **stop this command and run setup first**:
+Before anything else, call `setup_status`. If it reports `Current config: not found` (or the path exists but `setup_status` shows 0 detected providers with a missing-config note), **stop this command and run setup first**:
 
 1. Invoke the `agestra:setup` skill (or `/agestra setup` inline) — provider detection, selection, locale, `setup_apply`.
 2. After the config is written, resume this `/agestra design` command **from Step 1**, preserving `$ARGUMENTS`. Do not ask the user to retype.
 
-Agestra uses a single plugin-scoped `providers.config.json`. No config → no sanctioned provider set → setup is the only correct starting point.
+Agestra uses a single plugin-scoped `providers.config.json` (`$CLAUDE_PLUGIN_ROOT/providers.config.json` or `~/.agestra/providers.config.json`). No config → no sanctioned provider set → setup is the only correct starting point. Auto-detect without explicit setup can silently include disabled providers.
 
 ## Step 1: Determine design subject
 
@@ -34,47 +34,57 @@ If `$ARGUMENTS` is provided, use it directly as the subject.
 
 ## Step 2: Check environment and select mode
 
-Call `environment_check` to determine which providers and modes are available.
+Call `environment_check` and `provider_list` to determine which providers and modes are available.
 
 - If **no providers are available**: run the `agestra:agestra-designer` host specialist directly (Leader-host only) with the subject as context. The designer will ask questions to understand intent, explore the codebase for existing patterns, propose 2-3 approaches with trade-offs, refine based on feedback, and produce a design document in `docs/plans/`. Skip to presenting the result.
 - If **1+ providers are available**: proceed to consensus debate execution below.
 
+Respect the providers list verbatim. A provider marked `Not found`, unavailable in `environment_check`, or disabled by setup MUST NOT be invoked. Do not probe disabled providers.
+
 ## Step 3: Execute consensus debate
 
-**팀 구성:** `agestra:agestra-moderator` (조율) + `agestra:agestra-designer` (현재 호스트의 설계 전문 에이전트) + 사용 가능한 외부 AI (gemini, codex, ollama 등)
-
-1. Independent work + initial aggregation:
-
-   a. In parallel:
-      - Spawn the `agestra:agestra-designer` agent for host-local independent architecture exploration.
-        After the agent completes, save the host designer's result as a document via `workspace_create_document`:
-        - **title:** `Architecture Design — host/designer`
-        - **metadata:** `{ "Provider": "host/designer", "Task": "{subject}", "Mode": "Independent" }`
-        - **content:** The designer agent's full output.
-      - For each available provider, call `ai_chat` with `save_as_document` to let each AI produce its own document directly:
-        - **save_as_document.title:** `Architecture Design — {provider}`
-        - **save_as_document.metadata:** `{ "Task": "{subject}", "Mode": "Independent" }`
-        - **prompt:**
-
-          > Create a complete design document for [subject]. Include: 1) Problem definition — what exactly we're solving and why. 2) Constraints and requirements — technical limits, compatibility needs, performance targets. 3) 2-3 architecture approaches — each with detailed pros/cons, component diagrams, data flow, and effort estimates. 4) Recommended approach — pick one and justify the choice. 5) Implementation plan — step-by-step build sequence with dependencies. 6) Risks and mitigations. Be thorough and detailed — this document will be debated and refined.
-          >
-          > Subject: [the design subject]
-
-   b. Collect all document IDs.
-
-   c. Spawn the `agestra:agestra-moderator` agent in **Independent Aggregation** mode:
-      - Pass the **document ID list**.
-      - Moderator reads each document via `workspace_read`.
-      - Moderator classifies: consensus approaches, unique ideas, disputed trade-offs.
-      - Moderator creates an **aggregated document** via `workspace_create_document`.
-      - The moderator's integrated document becomes the starting document.
-
-2. Structured consensus rounds:
-   a. Call `agent_debate_structured` with the design topic, participants, and independent design document IDs.
-   b. Let the MCP moderator engine own provider order, JSON turn packets, stance validation, durable consensus ledger persistence, and generated debate markdown.
-   c. Treat the generated markdown as a readable report; do not edit it to change consensus state.
-   d. If the session is `ready-for-approval`, call `agent_debate_approve`; otherwise use `agent_debate_continue` or `agent_debate_reject`.
-
-3. Present the final document:
-   - Consensus sections: marked as agreed
-   - Disputed sections: show split positions with each provider's rationale
+**팀 구성:** `agestra:agestra-moderator` (조율) + `agestra:agestra-designer` (현재 호스트의 설계 전문 에이전트) + `environment_check`가 Available로 보고한 외부 AI.
+
+Follow the structured consensus document model from `docs/superpowers/specs/2026-04-25-structured-consensus-documents-design.md`:
+
+| Artifact | Folder | Role |
+|----------|--------|------|
+| Individual design documents | `.agestra/workspace/individual/` | Raw first-pass source material from each participant |
+| Consensus ledger JSON | `.agestra/workspace/debates/` | Authoritative system state |
+| Aggregated debate Markdown | `.agestra/workspace/debates/` | Generated readable mirror of the JSON ledger |
+| Synthesis document | `.agestra/workspace/synthesis/` | Self-contained final design decision document |
+
+The JSON consensus ledger is the source of truth. Generated Markdown must not be parsed or hand-edited to change provider stances, item status, or consensus state.
+
+1. Start an approval-gated structured debate with `agent_debate_structured`.
+   - **topic:** the design subject.
+   - **participants:** only providers reported available by `environment_check` / `provider_list`, plus the host design specialist when the engine supports it.
+   - **scope:** the design subject plus any user-provided constraints, relevant existing design docs, and code areas that should anchor the design.
+   - **leader:** the current leader identity when known.
+   - **locale:** the setup locale when known.
+   - **individual_review_prompt:** ask each participant to create a complete design document with:
+     1. Problem definition — what exactly is being solved and why.
+     2. Constraints and requirements — technical limits, compatibility needs, performance targets.
+     3. 2-3 architecture approaches — each with pros/cons, component boundaries, data flow, and effort estimate.
+     4. Recommended approach — one choice with justification.
+     5. Implementation plan — step-by-step build sequence with dependencies.
+     6. Risks and mitigations.
+
+2. Let the MCP moderator engine own the consensus flow.
+   - The engine writes individual first-pass documents under `individual/`.
+   - The engine owns provider turn order, JSON turn packets, response validation, ledger updates, aggregated debate Markdown rendering, synthesis rendering, and the final terminal table.
+   - Participants submit explicit JSON stances through the MCP consensus turn packet.
+   - The leader/moderator must not infer agreement from prose and must not edit provider stances manually.
+   - There must be one generated aggregated debate Markdown document per run, not one Markdown document per provider turn or round.
+
+3. Use the approval gate.
+   - If the terminal report says the session is `ready-for-approval`, inspect the report and call exactly one of:
+     - `agent_debate_approve` to write the synthesis document.
+     - `agent_debate_continue` to run 3, 5, or 10 more rounds.
+     - `agent_debate_reject` to close without synthesis.
+   - If the result is `error`, do not approve; report the orchestration failure.
+
+4. Present the final result.
+   - Name the debate Markdown path, consensus JSON ledger path, approval snapshot path if surfaced, and synthesis document path if approved.
+   - Summarize accepted design decisions, excluded options, and unresolved/disputed items.
+   - Preserve each provider's rationale for disputed positions.