takt 0.41.0 → 0.43.0

package/builtins/en/workflows/frontend-maintenance.yaml

@@ -0,0 +1,499 @@
+name: frontend-maintenance
+description: Strict frontend maintenance workflow for existing production systems
+workflow_config:
+  provider_options:
+    codex:
+      network_access: true
+    opencode:
+      network_access: true
+max_steps: 30
+initial_step: plan
+loop_monitors:
+  - cycle:
+      - ai-antipattern-review-1st
+      - ai-antipattern-fix
+    threshold: 3
+    judge:
+      persona: supervisor
+      instruction: loop-monitor-ai-antipattern-fix
+      rules:
+        - condition: Healthy (making progress)
+          next: ai-antipattern-review-1st
+        - condition: Unproductive (no improvement)
+          next: reviewers_1
+  - cycle:
+      - reviewers_1
+      - fix
+    threshold: 3
+    judge:
+      persona: supervisor
+      instruction: loop-monitor-reviewers-fix
+      rules:
+        - condition: converging (findings decreasing, fixes applied)
+          next: reviewers_1
+        - condition: unproductive (same findings repeating)
+          next: supervise
+steps:
+  - name: plan
+    edit: false
+    persona: planner
+    policy:
+      - design-planning
+      - existing-system-respect
+    knowledge:
+      - frontend
+      - react
+      - architecture
+      - existing-system
+    provider_options:
+      claude:
+        allowed_tools:
+          - Read
+          - Glob
+          - Grep
+          - Bash
+          - WebSearch
+          - WebFetch
+    instruction: plan-maintenance
+    rules:
+      - condition: Task analysis and planning is complete
+        next: write_tests
+      - condition: Requirements are unclear and planning cannot proceed
+        next: ABORT
+    output_contracts:
+      report:
+        - name: plan.md
+          format: plan-frontend
+  - name: write_tests
+    edit: true
+    persona: coder
+    policy:
+      - coding
+      - testing
+      - existing-system-respect
+    knowledge:
+      - frontend
+      - react
+      - architecture
+      - unit-testing
+      - e2e-testing
+      - existing-system
+    provider_options:
+      claude:
+        allowed_tools:
+          - Read
+          - Glob
+          - Grep
+          - Edit
+          - Write
+          - Bash
+          - WebSearch
+          - WebFetch
+    required_permission_mode: edit
+    instruction: write-tests-maintenance
+    rules:
+      - condition: Test creation is complete
+        next: implement
+      - condition: Skipping test creation as target is not yet implemented
+        next: implement
+      - condition: Cannot proceed with test creation
+        next: plan
+      - condition: User input required for clarification
+        next: write_tests
+        requires_user_input: true
+        interactive_only: true
+    output_contracts:
+      report:
+        - name: test-report.md
+          format: test-report
+  - name: implement
+    edit: true
+    persona: coder
+    policy:
+      - coding
+      - testing
+      - design-fidelity
+      - existing-system-respect
+    session: refresh
+    knowledge:
+      - frontend
+      - react
+      - security
+      - architecture
+      - existing-system
+    provider_options:
+      claude:
+        allowed_tools:
+          - Read
+          - Glob
+          - Grep
+          - Edit
+          - Write
+          - Bash
+          - WebSearch
+          - WebFetch
+    instruction: implement-maintenance
+    rules:
+      - condition: Implementation is complete
+        next: ai-antipattern-review-1st
+      - condition: No implementation (report only)
+        next: ai-antipattern-review-1st
+      - condition: Cannot proceed with implementation
+        next: ai-antipattern-review-1st
+      - condition: User input required
+        next: implement
+        requires_user_input: true
+        interactive_only: true
+    output_contracts:
+      report:
+        - name: maintenance-scope.md
+          format: maintenance-scope
+        - name: coder-decisions.md
+          format: coder-decisions
+  - name: ai-antipattern-review-1st
+    edit: false
+    persona: ai-antipattern-reviewer
+    policy:
+      - review
+      - ai-antipattern
+      - existing-system-respect
+    provider_options:
+      claude:
+        allowed_tools:
+          - Read
+          - Glob
+          - Grep
+          - WebSearch
+          - WebFetch
+    instruction: ai-antipattern-review
+    rules:
+      - condition: No AI-specific issues found
+        next: reviewers_1
+      - condition: AI-specific issues detected
+        next: ai-antipattern-fix
+    output_contracts:
+      report:
+        - name: ai-antipattern-review.md
+          format: ai-antipattern-review
+    knowledge:
+      - existing-system
+  - name: ai-antipattern-fix
+    edit: true
+    persona: coder
+    policy:
+      - coding
+      - testing
+      - design-fidelity
+      - existing-system-respect
+    session: refresh
+    knowledge:
+      - frontend
+      - react
+      - security
+      - architecture
+      - existing-system
+    provider_options:
+      claude:
+        allowed_tools:
+          - Read
+          - Glob
+          - Grep
+          - Edit
+          - Write
+          - Bash
+          - WebSearch
+          - WebFetch
+    instruction: ai-antipattern-fix
+    pass_previous_response: false
+    rules:
+      - condition: AI Reviewer's issues have been fixed
+        next: ai-antipattern-review-1st
+      - condition: No fix needed (verified target files/spec)
+        next: ai-antipattern-no-fix
+      - condition: Unable to proceed with fixes
+        next: ai-antipattern-no-fix
+  - name: ai-antipattern-no-fix
+    edit: false
+    persona: architecture-reviewer
+    policy:
+      - review
+      - existing-system-respect
+    provider_options:
+      claude:
+        allowed_tools:
+          - Read
+          - Glob
+          - Grep
+    rules:
+      - condition: ai-antipattern-review-1st's findings are valid (fix required)
+        next: ai-antipattern-fix
+      - condition: ai-antipattern-fix's judgment is valid (no fix needed)
+        next: reviewers_1
+    instruction: arbitrate
+    knowledge:
+      - existing-system
+  - name: reviewers_1
+    parallel:
+      - name: arch-review
+        edit: false
+        persona: architecture-reviewer
+        policy:
+          - review
+          - existing-system-respect
+        knowledge:
+          - architecture
+          - frontend
+          - react
+          - existing-system
+        provider_options:
+          claude:
+            allowed_tools:
+              - Read
+              - Glob
+              - Grep
+              - WebSearch
+              - WebFetch
+        rules:
+          - condition: approved
+          - condition: needs_fix
+        instruction: review-arch
+        output_contracts:
+          report:
+            - name: architect-review.md
+              format: architecture-review
+      - name: frontend-review
+        edit: false
+        persona: frontend-reviewer
+        policy:
+          - review
+          - design-fidelity
+          - existing-system-respect
+        knowledge:
+          - frontend
+          - react
+          - existing-system
+        provider_options:
+          claude:
+            allowed_tools:
+              - Read
+              - Glob
+              - Grep
+              - WebSearch
+              - WebFetch
+        rules:
+          - condition: approved
+          - condition: needs_fix
+        instruction: review-frontend
+        output_contracts:
+          report:
+            - name: frontend-review.md
+              format: frontend-review
+      - name: testing-review
+        edit: false
+        persona: testing-reviewer
+        policy:
+          - review
+          - testing
+          - existing-system-respect
+        knowledge:
+          - unit-testing
+          - e2e-testing
+          - existing-system
+        provider_options:
+          claude:
+            allowed_tools:
+              - Read
+              - Glob
+              - Grep
+              - WebSearch
+              - WebFetch
+        rules:
+          - condition: approved
+          - condition: needs_fix
+        instruction: review-test
+        output_contracts:
+          report:
+            - name: testing-review.md
+              format: testing-review
+      - name: ai-antipattern-review-2nd
+        edit: false
+        persona: ai-antipattern-reviewer
+        policy:
+          - review
+          - ai-antipattern
+          - existing-system-respect
+        provider_options:
+          claude:
+            allowed_tools:
+              - Read
+              - Glob
+              - Grep
+              - WebSearch
+              - WebFetch
+        instruction: ai-antipattern-review
+        rules:
+          - condition: approved
+          - condition: needs_fix
+        output_contracts:
+          report:
+            - name: ai-antipattern-review.md
+              format: ai-antipattern-review
+        knowledge:
+          - existing-system
+    rules:
+      - condition: all("approved")
+        next: reviewers_2
+      - condition: any("needs_fix")
+        next: fix
+  - name: reviewers_2
+    parallel:
+      - name: security-review
+        edit: false
+        persona: security-reviewer
+        policy:
+          - review
+          - existing-system-respect
+        knowledge:
+          - security
+          - existing-system
+        provider_options:
+          claude:
+            allowed_tools:
+              - Read
+              - Glob
+              - Grep
+              - WebSearch
+              - WebFetch
+        rules:
+          - condition: approved
+          - condition: needs_fix
+        instruction: review-security
+        output_contracts:
+          report:
+            - name: security-review.md
+              format: security-review
+      - name: qa-review
+        edit: false
+        persona: qa-reviewer
+        policy:
+          - review
+          - qa
+          - existing-system-respect
+        provider_options:
+          claude:
+            allowed_tools:
+              - Read
+              - Glob
+              - Grep
+              - WebSearch
+              - WebFetch
+        rules:
+          - condition: approved
+          - condition: needs_fix
+        instruction: review-qa
+        output_contracts:
+          report:
+            - name: qa-review.md
+              format: qa-review
+        knowledge:
+          - existing-system
+    rules:
+      - condition: all("approved")
+        next: supervise
+      - condition: any("needs_fix")
+        next: fix
+  - name: fix
+    edit: true
+    persona: coder
+    policy:
+      - coding
+      - testing
+      - design-fidelity
+      - existing-system-respect
+    knowledge:
+      - frontend
+      - react
+      - security
+      - architecture
+      - existing-system
+    provider_options:
+      claude:
+        allowed_tools:
+          - Read
+          - Glob
+          - Grep
+          - Edit
+          - Write
+          - Bash
+          - WebSearch
+          - WebFetch
+    required_permission_mode: edit
+    pass_previous_response: false
+    rules:
+      - condition: Fix complete
+        next: reviewers_1
+      - condition: Cannot proceed, insufficient info
+        next: plan
+    instruction: fix-maintenance
+  - name: supervise
+    edit: false
+    persona: dual-supervisor
+    policy:
+      - review
+      - existing-system-respect
+    provider_options:
+      claude:
+        allowed_tools:
+          - Read
+          - Glob
+          - Grep
+          - WebSearch
+          - WebFetch
+    instruction: supervise-maintenance
+    pass_previous_response: false
+    rules:
+      - condition: All validations pass and ready to merge
+        next: COMPLETE
+      - condition: Issues detected during final review
+        next: fix_supervisor
+    output_contracts:
+      report:
+        - name: supervisor-validation.md
+          format: supervisor-validation
+        - name: summary.md
+          format: summary
+          use_judge: false
+    knowledge:
+      - existing-system
+  - name: fix_supervisor
+    edit: true
+    persona: coder
+    policy:
+      - coding
+      - testing
+      - design-fidelity
+      - existing-system-respect
+    knowledge:
+      - frontend
+      - react
+      - security
+      - architecture
+      - existing-system
+    provider_options:
+      claude:
+        allowed_tools:
+          - Read
+          - Glob
+          - Grep
+          - Edit
+          - Write
+          - Bash
+          - WebSearch
+          - WebFetch
+    instruction: fix-maintenance
+    pass_previous_response: false
+    rules:
+      - condition: Supervisor's issues have been fixed
+        next: supervise
+      - condition: Unable to proceed with fixes
+        next: plan

package/builtins/en/workflows/peer-review.yaml

@@ -1,5 +1,5 @@
 name: peer-review
-description: takt-default Phase 2. Five parallel peer reviewers (+ ai-antipattern-review-2nd) ⇄ fix loop.
+description: takt-default Phase 2. Six parallel peer reviewers (+ ai-antipattern-review-2nd) ⇄ fix loop.
 subworkflow:
   callable: true
   visibility: internal
@@ -151,6 +151,28 @@ steps:
           report:
             - name: requirements-review.md
               format: requirements-review
+      - name: coding-review
+        edit: false
+        persona: coding-reviewer
+        policy: review
+        pass_previous_response: false
+        provider_options:
+          claude:
+            allowed_tools:
+              - Read
+              - Glob
+              - Grep
+              - Bash
+              - WebSearch
+              - WebFetch
+        instruction: review-coding
+        rules:
+          - condition: approved
+          - condition: needs_fix
+        output_contracts:
+          report:
+            - name: coding-review.md
+              format: coding-review
       - name: ai-antipattern-review-2nd
         edit: false
         persona: ai-antipattern-reviewer

package/builtins/en/workflows/review-fix-takt-default.yaml

@@ -1,5 +1,5 @@
 name: review-fix-takt-default
-description: "TAKT-focused multi-perspective review + fix loop (6-parallel initial review, AI antipattern pre-review on fix iterations)"
+description: "TAKT-focused multi-perspective review + fix loop (6-parallel initial review, AI antipattern pre-review on fix iterations, supervisor-finding fixes)"
 workflow_config:
   provider_options:
     codex:
@@ -334,7 +334,7 @@ steps:
       - condition: All checks passed
         next: COMPLETE
       - condition: Requirements unmet, tests failing, build errors
-        next: ABORT
+        next: fix_supervisor
     output_contracts:
       report:
         - name: supervisor-validation.md
@@ -342,3 +342,31 @@ steps:
         - name: summary.md
           format: summary
           use_judge: false
+  - name: fix_supervisor
+    edit: true
+    persona: coder
+    policy:
+      - coding
+      - testing
+    knowledge:
+      - takt
+      - architecture
+    provider_options:
+      claude:
+        allowed_tools:
+          - Read
+          - Glob
+          - Grep
+          - Edit
+          - Write
+          - Bash
+          - WebSearch
+          - WebFetch
+    required_permission_mode: edit
+    instruction: fix-supervisor
+    pass_previous_response: false
+    rules:
+      - condition: Fixes for supervisor findings complete
+        next: supervise
+      - condition: Unable to proceed with fixes
+        next: supervise

package/builtins/ja/config.yaml

@@ -91,10 +91,18 @@ language: ja         # 表示言語: ja | en
 # runtime:
 #   prepare: [node, gradle, ./custom-script.sh]
 
+# workflow YAML command gate ポリシー
+# workflow_command_gates:
+#   custom_scripts: false
+
 # ワークフローレベルのオーバーライド
 # workflow_overrides:
 #   quality_gates:
-#     - "All tests pass"
+#     - "All tests pass" # AI への完了条件
+#     - type: command    # step 完了時に機械実行される gate
+#       name: quality-check
+#       command: "./.takt/quality-gates/check.sh"
+#       timeout_ms: 300000
 #   quality_gates_edit_only: true
 #   steps:
 #     review:

package/builtins/ja/facets/instructions/dual-team-leader-implement.md

@@ -6,10 +6,13 @@
 
 1. 分解の可否を判断する
    - 変更対象ファイルを特定し、ファイル間の依存関係を確認する
-   - 横断的関心事（共有型・ID・イベント）がある場合は分解せず1パートで実装する
+   - まず並行可能な責務境界を探す
+   - 横断的関心事（共有型・ID・イベント）がある場合も、基盤 part → 消費 part → 検証 part に段階分けできるか検討する
    - 変更ファイル数が少ない場合、リファクタ・リネーム系の場合も1パートで実装する
+   - `parts.length === 1` になる場合も、検証分離や段階分けができないか先に検討する
+   - 「実装と検証」のような巨大な単一 part は避ける
 
-2. 分解する場合: フロントエンドとバックエンドでの分割を優先的に検討する
+2. 分解する場合: フロントエンドとバックエンドでの分割を優先的に検討し、難しい場合はファイルをレイヤー/モジュール単位でグループ化する
    - **デザイン参照があり、バックエンド変更が明示要件でない場合は分解しない。** UI の見た目・構造・文言・間隔は相互依存が強く、分割すると忠実再現を壊しやすいため、1パートでまとめて実装する
    - **デザイン参照がある場合、同一画面を構成する UI コンポーネント群は同じパートにまとめる。** ヘッダー・フィルタ・カード・バナー・モーダルなど、見た目の整合性に関わる要素を別パートへ分散しない
    - フロントエンド（UI・コンポーネント・スタイル）とバックエンド（API・ロジック・データ層）で分けるのが最も自然な分割軸
@@ -19,6 +22,7 @@
    - 型・インターフェースの依存がある場合は、依存元と依存先を同じグループにまとめる
    - 1つのファイルを複数のパートに割り当てない
    - テストファイルと実装ファイルは同じパートにまとめる
+   - 実装 part と検証 part を分ける
 
 3. 各パートに排他的なファイル担当を割り当てる
    - 各パートの instruction に以下を必ず明記する：
@@ -32,6 +36,7 @@
    - テスト済みの場合は「既存テストがパスするよう実装する」と明記する
    - 品質ゲート（Quality Gates）を参照し、必要な検証は専用の単独パートとして計画する
    - 並列の実装パートには、全体ビルド・全体テストを重複して実行させない
+   - npm test / npm run test:e2e:mock は各実装 part に重複して持たせない
 
 **制約:**
 - テストやビルドが必要な場合は、他パートの変更が揃った後に、単独の検証パートで実行する

package/builtins/ja/facets/instructions/fix-maintenance.md

@@ -0,0 +1,43 @@
+Report Directory内のレビューレポートを確認し、指摘事項を既存契約を保つ最小差分で修正してください。
+
+**修正の原則:**
+- 指摘の「修正案」が示されている場合はそれに沿った対応を優先し、独自の迂回策を取らない
+- 指摘の対象コードを直接修正すること。テストやドキュメントの追加で指摘を回避しない
+- 指摘を「修正必須」「確認のみ」「要求外」に分ける
+- 修正必須の指摘だけを対象にする
+- 指摘対象外のリファクタ、改名、コメント削除、テスト期待値変更を混ぜない
+
+**レポート参照方針:**
+- Report Directory内の最新レビューレポートを一次情報として参照してください。
+- 過去イテレーションのレポートは `{ファイル名}.{タイムスタンプ}` 形式で同ディレクトリに保存されています（例: `architect-review.md.20260304T123456Z`）。各レポートについて `{レポート名}.*` パターンで Glob を実行し、タイムスタンプ降順で最大2件まで読み、persists / reopened の傾向を把握してから修正に入ること。
+
+**完了条件（以下をすべて満たすこと）:**
+- 今回受け取った全指摘（new / reopened）のうち、修正必須のものを修正したこと
+- 同一 `family_tag` の潜在箇所を同時に修正したこと（部分修正で再発させない）
+- `family_tag` ごとに最低1件の再発防止テストを追加したこと（config契約/境界チェック系は必須）
+- 複数レビュアーから同一 `family_tag` の指摘が届いている場合は1件に統合して対応したこと
+- 修正後に全差分を確認し、指摘や要求と無関係な変更を戻したこと
+
+**重要**: 修正後、ビルド（型チェック）とテストを必ず実行してください。
+
+**必須出力（見出しを含める）**
+## 作業結果
+- {実施内容の要約}
+## 指摘への対応
+- {修正必須、確認のみ、要求外の分類と対応}
+## 変更内容
+- {必須変更と関連変更の要約}
+## 戻した不要変更
+- {戻した変更。なければ「なし」}
+## ビルド結果
+- {ビルド実行結果}
+## テスト結果
+- {テスト実行コマンドと結果}
+## 収束ゲート
+| 指標 | 件数 |
+|------|------|
+| new（今回修正） | {N} |
+| reopened（再発修正） | {N} |
+| persists（前回から継続、今回未着手） | {N} |
+## 証拠
+- {確認したファイル/検索/差分/ログの要点を列挙}