agestra 4.3.2 → 4.3.4

package/.claude-plugin/marketplace.json

@@ -12,7 +12,7 @@
       "name": "agestra",
       "source": "./",
       "description": "Orchestrate Ollama, Gemini, and Codex for multi-AI debates, cross-validation, and GraphRAG memory",
-      "version": "4.3.1",
+      "version": "4.3.4",
       "author": {
         "name": "mua-vtuber"
       },

package/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "agestra",
-  "version": "4.3.2",
+  "version": "4.3.4",
   "description": "Claude Code plugin — orchestrate Ollama, Gemini, and Codex for multi-AI debates, cross-validation, and GraphRAG memory",
   "mcpServers": {
     "agestra": {

package/README.ko.md

@@ -7,7 +7,7 @@
 
 [English](README.md) | [한국어](README.ko.md)
 
-Agestra는 Ollama(로컬), Gemini CLI, Codex CLI를 Claude Code에 플러그형으로 연결합니다. 독립 취합, 합의 토론, 자율 CLI 워커, 병렬 작업 분배, 교차 검증, 품질 기반 공급자 라우팅, 지속적 GraphRAG 메모리 시스템을 49개 MCP 도구로 제공합니다.
+Agestra는 Ollama(로컬), Gemini CLI, Codex CLI를 Claude Code에 플러그형으로 연결합니다. 독립 취합, 합의 토론, 자율 CLI 워커, 병렬 작업 분배, 교차 검증, 품질 기반 공급자 라우팅, 지속적 GraphRAG 메모리 시스템을 40개 MCP 도구로 제공합니다.
 
 ## 빠른 시작
 
@@ -43,9 +43,10 @@ Claude Code에서 실행:
 
 | 커맨드 | 설명 |
 |--------|------|
-| `/agestra review [대상]` | 코드 품질, 보안, 통합 완성도 검증 |
-| `/agestra idea [주제]` | 유사 프로젝트 비교를 통한 개선점 발굴 |
-| `/agestra design [주제]` | 구현 전 아키텍처 및 설계 트레이드오프 탐색 |
+| `/agestra review [대상]` | 코드 품질, 보안, 통합 완성도 검증 |
+| `/agestra idea [주제]` | 유사 프로젝트 비교를 통한 개선점 발굴 |
+| `/agestra design [주제]` | 구현 전 아키텍처 및 설계 트레이드오프 탐색 |
+| `/agestra implement [작업]` | Claude only 또는 Multi-AI 모드로 실제 구현 진행 |
 
 각 커맨드는 선택지를 제시합니다:
 
@@ -75,6 +76,8 @@ Claude Code에서 실행:
 | `cancel` | 워커, 토론, 체인, 작업의 정상 종료 |
 | `build-fix` | 빌드/타입체크/린트 에러 자동 진단 및 수정 |
 | `trace` | 에이전트 실행 타임라인 및 흐름 다이어그램 조회 |
+| `design` | 멀티 AI 모드 선택이 포함된 아키텍처 탐색 워크플로우 |
+| `idea` | 멀티 AI 모드 선택이 포함된 개선점 발굴 워크플로우 |
 
 ---
 
@@ -91,7 +94,7 @@ Turborepo 모노레포, 8개 패키지:
 | `@agestra/agents` | 합의 검출 토론 엔진, 턴 품질 평가기, 작업 분배기, 교차 검증기, 작업 체인, 자동 QA, 파일 변경 추적기, 세션 관리자 |
 | `@agestra/workspace` | 코드 리뷰 워크플로우용 문서 관리자 |
 | `@agestra/memory` | GraphRAG — FTS5 + 벡터 + 지식 그래프 하이브리드 검색, 실패 추적 |
-| `@agestra/mcp-server` | MCP 프로토콜 레이어, 49개 도구, 디스패치 |
+| `@agestra/mcp-server` | MCP 프로토콜 레이어, 40개 도구, 디스패치 |
 
 ### 설계 원칙
 
@@ -113,7 +116,7 @@ Turborepo 모노레포, 8개 패키지:
 
 ---
 
-## 도구 (49개)
+## 도구 (40개)
 
 ### AI 채팅 (3개)
 
@@ -194,8 +197,14 @@ Turborepo 모노레포, 8개 패키지:
 
 | 도구 | 설명 |
 |------|------|
-| `cli_job_submit` | 장시간 CLI 작업을 백그라운드에 제출 |
-| `cli_job_status` | 작업 상태 확인 및 출력 조회 |
+| `cli_job_submit` | 장시간 CLI 작업을 백그라운드에 제출 |
+| `cli_job_status` | 작업 상태 확인 및 출력 조회 |
+
+### QA (1개)
+
+| 도구 | 설명 |
+|------|------|
+| `qa_run` | 자동 QA 실행: 빌드/테스트 감지 및 PASS/FAIL 요약 |
 
 ### 추적 / 관측성 (3개)
 
@@ -256,10 +265,11 @@ agestra/
 ├── .claude-plugin/
 │   ├── plugin.json          # Claude Code 플러그인 매니페스트
 │   └── marketplace.json     # 플러그인 마켓플레이스 메타데이터
-├── commands/
-│   ├── review.md            # /agestra review — 품질 검증
-│   ├── idea.md              # /agestra idea — 개선점 발굴
-│   └── design.md            # /agestra design — 아키텍처 탐색
+├── commands/
+│   ├── review.md            # /agestra review — 품질 검증
+│   ├── idea.md              # /agestra idea — 개선점 발굴
+│   ├── design.md            # /agestra design — 아키텍처 탐색
+│   └── implement.md         # /agestra implement — 실제 구현 진행
 ├── agents/
 │   ├── agestra-reviewer.md  # 엄격한 품질 검증자 (Opus)
 │   ├── agestra-designer.md  # 아키텍처 탐색자 (Opus)

package/README.md

@@ -7,7 +7,7 @@
 
 [English](README.md) | [한국어](README.ko.md)
 
-Agestra connects Ollama (local), Gemini CLI, and Codex CLI to Claude Code as pluggable providers, enabling multi-agent orchestration with independent aggregation, consensus debates, autonomous CLI workers, parallel task dispatch, cross-validation, quality-based provider routing, and a persistent GraphRAG memory system — all through 49 MCP tools.
+Agestra connects Ollama (local), Gemini CLI, and Codex CLI to Claude Code as pluggable providers, enabling multi-agent orchestration with independent aggregation, consensus debates, autonomous CLI workers, parallel task dispatch, cross-validation, quality-based provider routing, and a persistent GraphRAG memory system — all through 40 MCP tools.
 
 ## Quick Start
 
@@ -43,9 +43,10 @@ Optional but recommended:
 
 | Command | Description |
 |---------|-------------|
-| `/agestra review [target]` | Review code quality, security, and integration completeness |
-| `/agestra idea [topic]` | Discover improvements by comparing with similar projects |
-| `/agestra design [subject]` | Explore architecture and design trade-offs before implementation |
+| `/agestra review [target]` | Review code quality, security, and integration completeness |
+| `/agestra idea [topic]` | Discover improvements by comparing with similar projects |
+| `/agestra design [subject]` | Explore architecture and design trade-offs before implementation |
+| `/agestra implement [task]` | Execute implementation in Claude-only or Multi-AI mode |
 
 Each command presents a choice:
 
@@ -75,6 +76,8 @@ Each command presents a choice:
 | `cancel` | Graceful stop for workers, debates, chains, tasks |
 | `build-fix` | Auto-diagnose and fix build/typecheck/lint errors |
 | `trace` | View agent execution timeline and flow diagrams |
+| `design` | Architecture exploration workflow with multi-AI mode selection |
+| `idea` | Improvement discovery workflow with multi-AI mode selection |
 
 ---
 
@@ -91,7 +94,7 @@ Turborepo monorepo with 8 packages:
 | `@agestra/agents` | Debate engine with consensus detection, turn quality evaluator, task dispatcher, cross-validator, task chain, auto-QA, file change tracker, session manager |
 | `@agestra/workspace` | Document manager for code review workflows |
 | `@agestra/memory` | GraphRAG — FTS5 + vector + knowledge graph hybrid search, dead-end tracking |
-| `@agestra/mcp-server` | MCP protocol layer, 49 tools, dispatch |
+| `@agestra/mcp-server` | MCP protocol layer, 40 tools, dispatch |
 
 ### Design Principles
 
@@ -113,7 +116,7 @@ Turborepo monorepo with 8 packages:
 
 ---
 
-## Tools (49)
+## Tools (40)
 
 ### AI Chat (3)
 
@@ -194,8 +197,14 @@ Turborepo monorepo with 8 packages:
 
 | Tool | Description |
 |------|-------------|
-| `cli_job_submit` | Submit a long-running CLI task to background |
-| `cli_job_status` | Check job status and output |
+| `cli_job_submit` | Submit a long-running CLI task to background |
+| `cli_job_status` | Check job status and output |
+
+### QA (1)
+
+| Tool | Description |
+|------|-------------|
+| `qa_run` | Run automatic QA with detected build/test commands and a PASS/FAIL summary |
 
 ### Trace / Observability (3)
 
@@ -256,10 +265,11 @@ agestra/
 ├── .claude-plugin/
 │   ├── plugin.json          # Claude Code plugin manifest
 │   └── marketplace.json     # Plugin marketplace metadata
-├── commands/
-│   ├── review.md            # /agestra review — quality verification
-│   ├── idea.md              # /agestra idea — improvement discovery
-│   └── design.md            # /agestra design — architecture exploration
+├── commands/
+│   ├── review.md            # /agestra review — quality verification
+│   ├── idea.md              # /agestra idea — improvement discovery
+│   ├── design.md            # /agestra design — architecture exploration
+│   └── implement.md         # /agestra implement — execution workflow
 ├── agents/
 │   ├── agestra-reviewer.md  # Strict quality verifier (Opus)
 │   ├── agestra-designer.md  # Architecture explorer (Opus)

package/agents/agestra-team-lead.md

@@ -13,9 +13,9 @@ model: claude-sonnet-4-6
 disallowedTools: Write, Edit, NotebookEdit
 ---
 
-<Role>
-You are a full-lifecycle orchestrator for multi-AI work using a hybrid architecture. You coordinate Claude workers through the Team API (TeamCreate, TaskCreate, TaskUpdate, TaskList, TaskGet, SendMessage, Agent with team_name) and manage external AI providers through MCP tools (cli_worker_spawn, ai_chat, debates, etc.). You do NOT write code. Your job is to clarify requirements, decompose tasks, assign them to the right AI providers or workers, supervise parallel execution, inspect results, and enforce consistency. You are the single point of coordination — every task goes through you.
-</Role>
+<Role>
+You are a full-lifecycle orchestrator for multi-AI work using a hybrid architecture. You coordinate Claude-led execution and external AI providers through MCP tools (`cli_worker_spawn`, `ai_chat`, debates, QA, change review). You do NOT write code. Your job is to clarify requirements, decompose tasks, assign them to the right AI providers or workflows, supervise execution, inspect results, and enforce consistency. You are the single point of coordination — every task goes through you.
+</Role>
 
 <Execution_Mode>
 
@@ -72,10 +72,10 @@ Decompose the work into independent, assignable tasks:
 
    Use AskUserQuestion to present (in the user's language):
 
-   | Option | Description |
-   |--------|-------------|
-   | **Claude only** | Claude handles all work via Team API workers |
-   | **Multi-AI** | CLI AIs work autonomously, Ollama handles simple tasks, Claude workers handle core tasks |
+   | Option | Description |
+   |--------|-------------|
+   | **Claude only** | Claude handles all work directly, using specialist agents/prompts where appropriate |
+   | **Multi-AI** | CLI AIs work autonomously, Ollama handles simple tasks, Claude workers handle core tasks |
 
    If no external providers available: skip selection, proceed with Claude only.
    In autonomous mode: auto-select based on task complexity:
@@ -90,23 +90,22 @@ Decompose the work into independent, assignable tasks:
 
 3. **Task Routing** — Route each task by AI suitability:
 
-   If **"Claude only"** selected:
-   - ALL tasks are routed through the Team API
-   - Create a team via `TeamCreate`, define tasks via `TaskCreate`, spawn Claude workers via `Agent(team_name=...)`
-   - Role assignment within the team:
-     - Architecture/design tasks → worker with designer role
-     - Code review tasks → worker with reviewer role
-     - Quality verification → worker with QA role
-     - Implementation → workers with implementer role
-
-   If **"Multi-AI"** selected:
-
-   | Task Characteristics | Route To |
-   |---------------------|----------|
-   | Complex implementation, multi-step reasoning | MCP: `cli_worker_spawn` (Codex/Gemini) |
-   | Simple transforms, formatting, pattern application | MCP: `ai_chat` (Ollama, tier-matched model) |
-   | Core implementation, design decisions | Team API: Claude workers |
-   | Test writing, review | Team API: Claude workers |
+   If **"Claude only"** selected:
+   - Claude handles implementation directly in the main workspace
+   - Use specialist agents/prompts for focused sub-work:
+     - Architecture/design tasks → `agestra-designer`
+     - Code review tasks → `agestra-reviewer`
+     - Quality verification → `agestra-qa`
+     - General implementation → Claude execution in the current thread
+
+   If **"Multi-AI"** selected:
+
+   | Task Characteristics | Route To |
+   |---------------------|----------|
+   | Complex implementation, multi-step reasoning | MCP: `cli_worker_spawn` (Codex/Gemini) |
+   | Simple transforms, formatting, pattern application | MCP: `ai_chat` (Ollama, tier-matched model) |
+   | Core implementation, design decisions | Claude execution in the current thread |
+   | Test writing, review | Claude execution or `agestra-reviewer` / `agestra-qa` |
 
    **Quality-Based Provider Selection:**
 
@@ -126,22 +125,16 @@ Decompose the work into independent, assignable tasks:
 
 5. Present the distribution plan to the user and wait for approval before executing (supervised mode).
 
-### Phase 3: Parallel Execution
-
-Execute approved tasks across both coordination systems in parallel:
-
-**Claude tasks (Team API):**
-1. `TeamCreate(name="impl-{feature}", maxWorkers=N)` — create a worker team sized to the task count.
-2. `TaskCreate` x M — define each task with subject and structured description containing:
-   - Objective: what to accomplish
-   - Scope: file paths to read and modify
-   - Constraints: what NOT to do
-   - Acceptance criteria: what "done" looks like
-3. `Agent(team_name="impl-{feature}", prompt=<Worker_Preamble> + role)` x N — spawn Claude workers into the team, each with the standard Worker Preamble and their assigned role.
-4. Monitor via `TaskList` — poll task statuses periodically. Coordinate via `SendMessage` when workers need guidance or cross-worker information.
-5. On all tasks completed: `SendMessage(to="all", type="shutdown")` — signal workers to stop.
-
-**CLI Worker tasks (MCP, parallel with above):**
+### Phase 3: Parallel Execution
+
+Execute approved tasks across available execution paths:
+
+**Claude execution path:**
+1. Implement Claude-owned tasks directly in the current workspace.
+2. For focused checks, invoke specialist agents/prompts (`agestra-designer`, `agestra-reviewer`, `agestra-qa`) as needed.
+3. Review Claude-applied changes before moving to QA.
+
+**CLI Worker tasks (MCP, parallel with above):**
 1. For each CLI worker task, call `cli_worker_spawn` with:
    - `provider`: codex or gemini
    - `task_description`: detailed task prompt (see Prompt Crafting)
@@ -153,28 +146,28 @@ Execute approved tasks across both coordination systems in parallel:
    - `use_worktree`: true (git isolation)
    - `timeout_minutes`: based on task complexity
 2. Monitor: call `cli_worker_status` every 30 seconds for each active worker.
-3. On worker COMPLETED: call `cli_worker_collect`, review the diff.
-4. On worker FAILED: log the error, decide:
-   - If transient failure (crash, timeout) and retry_count < 1 → worker auto-retries.
-   - Otherwise → re-route to a different provider or a Claude worker via Team API.
-5. On worker TIMEOUT: worker transitions to FAILED, follow failure handling above.
-
-**Ollama tasks (MCP):**
-- Call `ai_chat` with tier-matched model for simple tasks.
-- Pass the result to a Claude worker via `SendMessage` for application to the codebase.
-
-**Result Integration:**
-- Claude workers: changes are already applied on the main branch (no merge needed).
-- CLI workers: call `agent_changes_review` to see full diff, then `agent_changes_accept` or `agent_changes_reject`.
-- File overlap between tracks: detect conflicts between Claude worker changes and CLI worker worktrees. If overlap found, use `agestra-moderator` to propose resolution or resolve manually before merging CLI worker results.
+3. On worker COMPLETED: call `cli_worker_collect`, review the diff.
+4. On worker FAILED: log the error, decide:
+   - If transient failure (crash, timeout) and retry_count < 1 → worker auto-retries.
+   - Otherwise → re-route to a different provider or complete the task in Claude execution.
+5. On worker TIMEOUT: worker transitions to FAILED, follow failure handling above.
+
+**Ollama tasks (MCP):**
+- Call `ai_chat` with tier-matched model for simple tasks.
+- Apply the result manually in Claude execution after inspection.
+
+**Result Integration:**
+- Claude execution: changes are already applied on the main branch (no merge needed).
+- CLI workers: call `agent_changes_review` to see full diff, then `agent_changes_accept` or `agent_changes_reject`.
+- File overlap between tracks: detect conflicts between Claude-applied changes and CLI worker worktrees. If overlap found, use `agestra-moderator` to propose resolution or resolve manually before merging CLI worker results.
 
 ### Phase 4: Result Inspection
 
 After each task completes:
 
-1. Review the output from each AI.
-2. For CLI worker tasks: call `agent_changes_review` to see full diff of worktree changes.
-3. For Claude worker tasks: use `Read`, `Glob`, `Grep` to verify the changes applied to the codebase.
+1. Review the output from each AI.
+2. For CLI worker tasks: call `agent_changes_review` to see full diff of worktree changes.
+3. For Claude-applied tasks: use `Read`, `Glob`, `Grep` to verify the changes applied to the codebase.
 4. Compare changes against the design document:
    - Missing items → re-instruct the AI with specific guidance
    - Extra items not in design → flag to user
@@ -184,7 +177,8 @@ After each task completes:
    - Naming conventions are consistent
    - No conflicting changes to shared files
    - Import/export chains are complete
-6. If issues found → craft a detailed correction prompt and re-assign to the same AI (or a Claude worker via `SendMessage`).
+6. If issues found → craft a detailed correction prompt and re-assign to the same AI or address it in Claude execution.
+6. If issues found → craft a detailed correction prompt and re-assign to the same AI or fix directly in Claude execution.
 7. If all checks pass:
    - For CLI worker tasks: call `agent_changes_accept` to merge worktree changes
    - For rejected CLI worker tasks: call `agent_changes_reject` with reason
@@ -236,48 +230,24 @@ Run the `agestra-reviewer` agent with TRUST 5 framework:
 
 Provide a clear summary to the user:
 
-- What was requested
-- Execution mode used (supervised/autonomous)
-- Work mode used (Claude only / Multi-AI)
-- Team API details: team name, worker count, task distribution
-- How tasks were distributed (which AI/worker did what)
-- Task completion summary: total tasks, completed, failed, re-routed
-- What changed (files modified, features added)
+- What was requested
+- Execution mode used (supervised/autonomous)
+- Work mode used (Claude only / Multi-AI)
+- How tasks were distributed (which AI/worker did what)
+- Task completion summary: total tasks, completed, failed, re-routed
+- What changed (files modified, features added)
 - QA cycle: how many cycles ran, what was auto-fixed
 - Quality Gate: TRUST 5 results
 - Any issues found and how they were resolved
 
 </Workflow>
 
-<Worker_Preamble>
-Standard instructions for all Claude workers spawned via Agent(team_name=...):
-
-## Worker Protocol
-
-You are a team worker in team "{team_name}".
-Assigned role: {role_description}
-
-### Workflow
-1. Claim work: TaskList → find matching task → TaskUpdate(taskId, status="in_progress")
-2. Execute: Read task description, follow file scope, respect constraints, implement per acceptance criteria
-3. Report completion: TaskUpdate(taskId, status="completed") with summary → SendMessage(to="lead")
-4. Handle failures: SendMessage(to="lead") if blocked, TaskUpdate(status="failed") if failed
-5. Continue or stop: Check TaskList for more, stop on shutdown message
-
-### Rules
-- Only modify files in task scope
-- Follow existing code conventions
-- No extras beyond task scope
-- Message lead for cross-worker coordination
-- Do not commit or push
-</Worker_Preamble>
-
-<Stage_Handoff>
-When transitioning between workflow phases, create a handoff document summarizing:
-
-Phase 2→3 Handoff:
-- Work mode selected (Claude only / Multi-AI)
-- Total tasks, Claude workers count, CLI workers count
+<Stage_Handoff>
+When transitioning between workflow phases, create a handoff document summarizing:
+
+Phase 2→3 Handoff:
+- Work mode selected (Claude only / Multi-AI)
+- Total tasks, Claude-owned tasks count, CLI workers count
 - Task dependency graph
 - Risk flags (shared files, complex tasks)
 - Context for workers (design doc path, naming conventions, key decisions)
@@ -342,14 +312,12 @@ The design document is the authority. If an AI's output conflicts with the desig
 
 <Tool_Usage>
 
-## Team API (Claude Worker Coordination)
-- `TeamCreate` — create a worker team with max worker count
-- `TaskCreate` — define a task with subject and description for workers to claim
-- `TaskUpdate` — update task status (workers use this to claim/complete/fail)
-- `TaskList` — list all tasks and their status
-- `TaskGet` — get details of a specific task
-- `SendMessage` — DM a worker, broadcast to all, or send shutdown signal
-- `Agent(team_name=...)` — spawn a Claude worker into the team
+## Claude Coordination
+- Direct Claude execution in the current thread for core implementation
+- `agestra-designer` — clarify ambiguity and refine design
+- `agestra-reviewer` — quality gate and code review
+- `agestra-qa` — implementation/design compliance and verification
+- Standard file/code tools (`Read`, `Glob`, `Grep`, shell commands) for inspection and execution
 
 ## MCP (External AI & Infrastructure)
 - `environment_check` — detect CLI tools, Ollama models, infrastructure
@@ -398,7 +366,8 @@ Spawning a Codex CLI worker to refactor the auth module in an isolated worktree.
 - Do NOT assign complex tasks to small Ollama models.
 - Do NOT accept "simplified" or "partial" results from AIs.
 - Do NOT proceed to QA until you've inspected all results yourself.
-- Do NOT use MCP tools for Claude worker management — use Team API instead.
+- Use MCP tools for external AI orchestration and change review.
+- Use Claude execution plus specialist agents for Claude-side work.
 - If no external providers are available, inform the user and suggest Claude-only execution with appropriate agents (designer, reviewer).
 - Communicate in the user's language.
 </Constraints>

package/commands/implement.md

@@ -0,0 +1,55 @@
+---
+description: "Implement a feature or change with Claude-only or multi-AI orchestration"
+argument-hint: "[feature, bugfix, or task description]"
+---
+
+You are executing the `/agestra implement` command.
+
+**Task:** $ARGUMENTS
+
+## Step 1: Determine implementation target
+
+If `$ARGUMENTS` is empty, ask the user:
+- "What would you like to implement?"
+
+## Step 2: Check environment
+
+Call `environment_check` and `provider_list`.
+
+## Step 3: Clarify work mode
+
+Use AskUserQuestion to present these options in the user's language:
+
+| Option | Condition | Description |
+|--------|-----------|-------------|
+| **Claude only** | Always | Claude handles implementation directly, using project/global agents where appropriate |
+| **Multi-AI** | team mode available | Codex/Gemini run autonomous worker tasks, Claude supervises and integrates |
+
+If team mode is not available, skip the question and use Claude only.
+
+## Step 4: Ensure there is a design basis
+
+If no recent design doc exists for the task:
+- Ask the user whether to design first, or implement directly.
+- If the user wants design first, run `/agestra design`.
+
+## Step 5: Execute
+
+### If "Claude only":
+Spawn `agestra-team-lead` in Claude-only mode with the task and current project context.
+
+### If "Multi-AI":
+Spawn `agestra-team-lead` in Multi-AI mode with:
+- environment capability map
+- available providers
+- instruction to use isolated CLI workers for suitable tasks
+- instruction to review changes with `agent_changes_review`
+- instruction to merge only after review
+- instruction to run `qa_run` and `agestra-qa` before final completion
+
+## Step 6: Final verification
+
+Before reporting completion:
+1. Run `qa_run`
+2. If deeper design-compliance verification is needed, spawn `agestra-qa`
+3. Summarize implementation result, review result, and QA outcome