fix: align TodoWrite memory model with task system docs

s05_todo_write/README.en.md

@@ -32,19 +32,21 @@ The dispatch mechanism is unchanged; the new tool is still routed through `TOOL_
 
 ## How It Works
 
-**The todo_write tool**, accepts a list with statuses, persists to `.tasks/current_todos.json` (teaching version writes to disk for observability), and displays progress in the terminal:
+**The todo_write tool** accepts a list with statuses, keeps it in the current process memory, and displays progress in the terminal:
 
 ```python
+CURRENT_TODOS: list[dict] = []
+
 def run_todo_write(todos: list) -> str:
-    tasks_file = TASKS_DIR / "current_todos.json"
-    tasks_file.write_text(json.dumps(todos, indent=2, ensure_ascii=False))
+    global CURRENT_TODOS
+    CURRENT_TODOS = todos
 
     lines = ["\n## Current Tasks"]
-    for t in todos:
+    for t in CURRENT_TODOS:
         icon = {"pending": " ", "in_progress": "▸", "completed": "✓"}[t["status"]]
         lines.append(f"  [{icon}] {t['content']}")
     print("\n".join(lines))
-    return f"Updated {len(todos)} tasks"
+    return f"Updated {len(CURRENT_TODOS)} tasks"
 ```
 
 The tool definition joins the other 5 in the dispatch map:
@@ -135,7 +137,7 @@ The Agent can plan now. But if a task is too large, say "refactor the entire aut
 
 CC has two task systems coexisting (`tasks.ts:133-139`):
 
-- **TodoWrite (V1)**: A simple list tool, data maintained in memory AppState (`TodoWriteTool.ts:65-103`). The teaching version writes to `.tasks/current_todos.json` for observability; the real V1 does not write to disk.
+- **TodoWrite (V1)**: A simple list tool, data maintained in memory AppState (`TodoWriteTool.ts:65-103`). The teaching version also keeps it in process memory and clears it on exit.
 - **Task System (V2 = s12)**: File-persisted, dependency graph, concurrency locks, ownership.
 
 The switch is controlled by `isTodoV2Enabled()`. In the current source: V2 is enabled by default in interactive sessions, V1 in non-interactive (SDK) sessions; setting `CLAUDE_CODE_ENABLE_TASKS` forces V2 regardless. Note the source comment "Force-enable tasks in non-interactive mode" describes the env var path's purpose, not the default branch's return semantics.

s05_todo_write/README.ja.md

@@ -32,19 +32,21 @@ Agent は作業を開始する。3 つのファイルをリネーム、テスト
 
 ## 仕組み
 
-**todo_write ツール**、ステータス付きのリストを受け取り、`.tasks/current_todos.json` に永続化（教育版は観察用にディスクに書き込む）、端末に進捗を表示する：
+**todo_write ツール**は、ステータス付きのリストを受け取り、現在のプロセスメモリに保持し、端末に進捗を表示する：
 
 ```python
+CURRENT_TODOS: list[dict] = []
+
 def run_todo_write(todos: list) -> str:
-    tasks_file = TASKS_DIR / "current_todos.json"
-    tasks_file.write_text(json.dumps(todos, indent=2, ensure_ascii=False))
+    global CURRENT_TODOS
+    CURRENT_TODOS = todos
 
     lines = ["\n## Current Tasks"]
-    for t in todos:
+    for t in CURRENT_TODOS:
         icon = {"pending": " ", "in_progress": "▸", "completed": "✓"}[t["status"]]
         lines.append(f"  [{icon}] {t['content']}")
     print("\n".join(lines))
-    return f"Updated {len(todos)} tasks"
+    return f"Updated {len(CURRENT_TODOS)} tasks"
 ```
 
 ツール定義は他の 5 つと一緒にディスパッチマップに追加される：
@@ -135,7 +137,7 @@ Agent は計画できるようになった。しかしタスクが大きすぎ
 
 CC には二つのタスクシステムが共存している（`tasks.ts:133-139`）：
 
-- **TodoWrite（V1）**：シンプルなリストツール、データはメモリ AppState で管理（`TodoWriteTool.ts:65-103`）。教育版は観察用に `.tasks/current_todos.json` に書き込むが、実際の V1 はディスクに書き込まない
+- **TodoWrite（V1）**：シンプルなリストツール、データはメモリ AppState で管理（`TodoWriteTool.ts:65-103`）。教育版もプロセスメモリに保持し、終了時に消える
 - **Task System（V2 = s12）**：ファイル永続化、依存グラフ、並行ロック、ownership
 
 切り替えは `isTodoV2Enabled()` で制御される。現在のソースコードの実装：対話型セッションでは V2 がデフォルトで有効、非対話型セッション（SDK）では V1 がデフォルトで有効。`CLAUDE_CODE_ENABLE_TASKS` 環境変数を設定するとセッション種別に関わらず V2 が強制有効になる。ソースコメント「Force-enable tasks in non-interactive mode」は環境変数パスの用途を説明しており、デフォルト分岐の戻り値のセマンティクスとは異なるため注意。

s05_todo_write/README.md

@@ -32,19 +32,21 @@ dispatch 机制不变，新工具仍然走 `TOOL_HANDLERS[block.name]` 分发。
 
 ## 工作原理
 
-**todo_write 工具**，接收一个带状态的列表，持久化到 `.tasks/current_todos.json`（教学版写盘以便观察），同时在终端显示进度：
+**todo_write 工具**，接收一个带状态的列表，保存在当前进程内存中，同时在终端显示进度：
 
 ```python
+CURRENT_TODOS: list[dict] = []
+
 def run_todo_write(todos: list) -> str:
-    tasks_file = TASKS_DIR / "current_todos.json"
-    tasks_file.write_text(json.dumps(todos, indent=2, ensure_ascii=False))
+    global CURRENT_TODOS
+    CURRENT_TODOS = todos
 
     lines = ["\n## Current Tasks"]
-    for t in todos:
+    for t in CURRENT_TODOS:
         icon = {"pending": " ", "in_progress": "▸", "completed": "✓"}[t["status"]]
         lines.append(f"  [{icon}] {t['content']}")
     print("\n".join(lines))
-    return f"Updated {len(todos)} tasks"
+    return f"Updated {len(CURRENT_TODOS)} tasks"
 ```
 
 工具定义和其他 5 个工具一起加入 dispatch map：
@@ -135,7 +137,7 @@ s06 Subagent → 把大任务拆成子任务，每个子任务派一个独立的
 
 CC 中有两套任务系统并存（`tasks.ts:133-139`）：
 
-- **TodoWrite（V1）**：一个简单的列表工具，数据在内存 AppState 中维护（`TodoWriteTool.ts:65-103`）。教学版写盘到 `.tasks/current_todos.json` 是为了可观察性，真实 V1 不写盘
+- **TodoWrite（V1）**：一个简单的列表工具，数据在内存 AppState 中维护（`TodoWriteTool.ts:65-103`）。教学版也保存在进程内存里，退出后清空
 - **Task System（V2 = s12）**：文件持久化、依赖图、并发锁、ownership
 
 切换由 `isTodoV2Enabled()` 控制。当前源码的实现逻辑：交互式会话中 V2 默认启用，非交互式会话（SDK）中 V1 默认启用；设置 `CLAUDE_CODE_ENABLE_TASKS` 环境变量可强制启用 V2。注意源码注释 "Force-enable tasks in non-interactive mode" 描述的是 env var 路径的用途，和默认分支的返回值语义不同，阅读时需区分。
@@ -153,4 +155,4 @@ Task System 相比 TodoWrite 的核心增量：
 
 </details>
 
-<!-- translation-sync: zh@v1, en@v0, ja@v0 -->
+<!-- translation-sync: zh@v1, en@v1, ja@v1 -->

s05_todo_write/code.py

@@ -12,7 +12,7 @@
                                       todo_write ← NEW
                                    +------------------+
                                         |
-                        .tasks/current_todos.json
+                         in-memory current_todos
                                         |
                         if rounds_since_todo >= 3:
                           inject <reminder>
@@ -28,7 +28,7 @@
 Needs: pip install anthropic python-dotenv + ANTHROPIC_API_KEY in .env
 """
 
-import os, subprocess, json
+import os, subprocess
 from pathlib import Path
 
 try:
@@ -45,9 +45,9 @@
     os.environ.pop("ANTHROPIC_AUTH_TOKEN", None)
 
 WORKDIR = Path.cwd()
-TASKS_DIR = WORKDIR / ".tasks"; TASKS_DIR.mkdir(exist_ok=True)
 client = Anthropic(base_url=os.getenv("ANTHROPIC_BASE_URL"))
 MODEL = os.environ["MODEL_ID"]
+CURRENT_TODOS: list[dict] = []
 
 # s05 change: SYSTEM prompt adds planning guidance
 SYSTEM = (
@@ -122,20 +122,20 @@ def run_glob(pattern: str) -> str:
 # ═══════════════════════════════════════════════════════════
 
 def run_todo_write(todos: list) -> str:
+    global CURRENT_TODOS
     # validate required fields
     for i, t in enumerate(todos):
         if "content" not in t or "status" not in t:
             return f"Error: todos[{i}] missing 'content' or 'status'"
         if t["status"] not in ("pending", "in_progress", "completed"):
             return f"Error: todos[{i}] has invalid status '{t['status']}'"
-    tasks_file = TASKS_DIR / "current_todos.json"
-    tasks_file.write_text(json.dumps(todos, indent=2, ensure_ascii=False))
+    CURRENT_TODOS = todos
     lines = ["\n\033[33m## Current Tasks\033[0m"]
-    for t in todos:
+    for t in CURRENT_TODOS:
         icon = {"pending": " ", "in_progress": "\033[36m▸\033[0m", "completed": "\033[32m✓\033[0m"}[t["status"]]
         lines.append(f"  [{icon}] {t['content']}")
     print("\n".join(lines))
-    return f"Updated {len(todos)} tasks"
+    return f"Updated {len(CURRENT_TODOS)} tasks"
 
 TOOLS = [
     {"name": "bash", "description": "Run a shell command.",

s06_subagent/code.py

@@ -28,7 +28,7 @@
 Needs: pip install anthropic python-dotenv + ANTHROPIC_API_KEY in .env
 """
 
-import os, subprocess, json
+import os, subprocess
 from pathlib import Path
 
 try:
@@ -45,9 +45,9 @@
     os.environ.pop("ANTHROPIC_AUTH_TOKEN", None)
 
 WORKDIR = Path.cwd()
-TASKS_DIR = WORKDIR / ".tasks"; TASKS_DIR.mkdir(exist_ok=True)
 client = Anthropic(base_url=os.getenv("ANTHROPIC_BASE_URL"))
 MODEL = os.environ["MODEL_ID"]
+CURRENT_TODOS: list[dict] = []
 
 SYSTEM = (
     f"You are a coding agent at {WORKDIR}. "
@@ -122,19 +122,19 @@ def run_glob(pattern: str) -> str:
         return f"Error: {e}"
 
 def run_todo_write(todos: list) -> str:
+    global CURRENT_TODOS
     for i, t in enumerate(todos):
         if "content" not in t or "status" not in t:
             return f"Error: todos[{i}] missing 'content' or 'status'"
         if t["status"] not in ("pending", "in_progress", "completed"):
             return f"Error: todos[{i}] has invalid status '{t['status']}'"
-    tasks_file = TASKS_DIR / "current_todos.json"
-    tasks_file.write_text(json.dumps(todos, indent=2, ensure_ascii=False))
+    CURRENT_TODOS = todos
     lines = ["\n\033[33m## Current Tasks\033[0m"]
-    for t in todos:
+    for t in CURRENT_TODOS:
         icon = {"pending": " ", "in_progress": "\033[36m▸\033[0m", "completed": "\033[32m✓\033[0m"}[t["status"]]
         lines.append(f"  [{icon}] {t['content']}")
     print("\n".join(lines))
-    return f"Updated {len(todos)} tasks"
+    return f"Updated {len(CURRENT_TODOS)} tasks"
 
 def extract_text(content) -> str:
     """Extract text from message content blocks."""

s07_skill_loading/code.py

@@ -26,7 +26,7 @@
 Needs: pip install anthropic python-dotenv + ANTHROPIC_API_KEY in .env
 """
 
-import os, subprocess, json
+import os, subprocess
 from pathlib import Path
 
 try:
@@ -44,9 +44,9 @@
 
 WORKDIR = Path.cwd()
 SKILLS_DIR = WORKDIR / "skills"
-TASKS_DIR = WORKDIR / ".tasks"; TASKS_DIR.mkdir(exist_ok=True)
 client = Anthropic(base_url=os.getenv("ANTHROPIC_BASE_URL"))
 MODEL = os.environ["MODEL_ID"]
+CURRENT_TODOS: list[dict] = []
 
 # s07: Skill catalog scan (used by build_system below)
 def _parse_frontmatter(text: str) -> tuple[dict, str]:
@@ -169,19 +169,19 @@ def run_glob(pattern: str) -> str:
         return f"Error: {e}"
 
 def run_todo_write(todos: list) -> str:
+    global CURRENT_TODOS
     for i, t in enumerate(todos):
         if "content" not in t or "status" not in t:
             return f"Error: todos[{i}] missing 'content' or 'status'"
         if t["status"] not in ("pending", "in_progress", "completed"):
             return f"Error: todos[{i}] has invalid status '{t['status']}'"
-    tasks_file = TASKS_DIR / "current_todos.json"
-    tasks_file.write_text(json.dumps(todos, indent=2, ensure_ascii=False))
+    CURRENT_TODOS = todos
     lines = ["\n\033[33m## Current Tasks\033[0m"]
-    for t in todos:
+    for t in CURRENT_TODOS:
         icon = {"pending": " ", "in_progress": "\033[36m▸\033[0m", "completed": "\033[32m✓\033[0m"}[t["status"]]
         lines.append(f"  [{icon}] {t['content']}")
     print("\n".join(lines))
-    return f"Updated {len(todos)} tasks"
+    return f"Updated {len(CURRENT_TODOS)} tasks"
 
 def extract_text(content) -> str:
     if not isinstance(content, list):

s08_context_compact/code.py

@@ -51,9 +51,9 @@
 SKILLS_DIR = WORKDIR / "skills"
 TRANSCRIPT_DIR = WORKDIR / ".transcripts"
 TOOL_RESULTS_DIR = WORKDIR / ".task_outputs" / "tool-results"
-TASKS_DIR = WORKDIR / ".tasks"; TASKS_DIR.mkdir(exist_ok=True)
 client = Anthropic(base_url=os.getenv("ANTHROPIC_BASE_URL"))
 MODEL = os.environ["MODEL_ID"]
+CURRENT_TODOS: list[dict] = []
 
 # s07: Skill catalog scan (inherited from s07)
 def _parse_frontmatter(text: str) -> tuple[dict, str]:
@@ -166,19 +166,19 @@ def run_glob(pattern: str) -> str:
     except Exception as e: return f"Error: {e}"
 
 def run_todo_write(todos: list) -> str:
+    global CURRENT_TODOS
     for i, t in enumerate(todos):
         if "content" not in t or "status" not in t:
             return f"Error: todos[{i}] missing 'content' or 'status'"
         if t["status"] not in ("pending", "in_progress", "completed"):
             return f"Error: todos[{i}] has invalid status '{t['status']}'"
-    tasks_file = TASKS_DIR / "current_todos.json"
-    tasks_file.write_text(json.dumps(todos, indent=2, ensure_ascii=False))
+    CURRENT_TODOS = todos
     lines = ["\n\033[33m## Current Tasks\033[0m"]
-    for t in todos:
+    for t in CURRENT_TODOS:
         icon = {"pending": " ", "in_progress": "\033[36m▸\033[0m", "completed": "\033[32m✓\033[0m"}[t["status"]]
         lines.append(f"  [{icon}] {t['content']}")
     print("\n".join(lines))
-    return f"Updated {len(todos)} tasks"
+    return f"Updated {len(CURRENT_TODOS)} tasks"
 
 def extract_text(content) -> str:
     if not isinstance(content, list): return str(content)

s12_task_system/README.en.md

@@ -16,7 +16,7 @@ The agent receives a project: set up a database, write APIs, add tests. It uses
 
 You can't build the roof before laying the foundation. Tasks have ordering. Task dependencies should form a Directed Acyclic Graph (DAG); the teaching version only demonstrates `blockedBy` checking, without cycle detection.
 
-s05's TodoWrite is a list. No dependencies, no persistence — when the conversation ends, the list is gone. What you need is a **task system**: each task is a JSON file, tasks have `blockedBy` dependencies, and they persist across sessions on disk.
+s05's TodoWrite is an execution checklist for the current task, kept in session memory. What you need here is a **task system**: each task is a JSON file, tasks have `blockedBy` dependencies, and they persist across sessions on disk.
 
 ---
 
@@ -30,11 +30,13 @@ TodoWrite vs Task System:
 
 | | TodoWrite (s05) | Task System (s12) |
 |---|---|---|
-| Storage | In-memory list | `.tasks/` JSON files |
-| Dependencies | None | `blockedBy` dependency graph |
-| Persistence | Lost when conversation ends | Cross-session |
-| Multi-agent | None | `owner` field |
-| Status | checked / unchecked | pending → in_progress → completed |
+| Role | Execution checklist for the current task | Recoverable task system |
+| Storage | In-process / session state | `.tasks/{id}.json` |
+| Dependencies | None | `blockedBy` / `blocks` graph |
+| Lifecycle | Current session / current task | Cross-session |
+| Coordination | No task claiming | `owner` / claim |
+| Status | pending / in_progress / completed | pending / in_progress / completed |
+| Granularity | The agent's own steps | Tasks that can be claimed, tracked, and unblocked |
 
 ---
 

s12_task_system/README.ja.md

@@ -16,7 +16,7 @@ Agent がプロジェクトを受けた：データベース構築、API 実装
 
 屋根を先に建てて基礎を後から打つことはできない。タスクには順序がある。タスクの依存関係は有向非巡回グラフ（DAG）を形成すべき；教学版は `blockedBy` チェックのみをデモし、循環検出は実装していない。
 
-s05 の TodoWrite はリスト。依存関係も永続化もなく、会話が終わればリストも消える。必要なのは**タスクシステム**：各タスクは JSON ファイル、タスク間に `blockedBy` 依存関係、ディスク上でセッションをまたいで永続化。
+s05 の TodoWrite は現在のタスクの実行チェックリストで、セッションメモリに保持される。ここで必要なのは**タスクシステム**：各タスクは JSON ファイル、タスク間に `blockedBy` 依存関係、ディスク上でセッションをまたいで永続化。
 
 ---
 
@@ -30,11 +30,13 @@ TodoWrite vs Task System：
 
 | | TodoWrite (s05) | Task System (s12) |
 |---|---|---|
-| ストレージ | メモリ内リスト | `.tasks/` JSON ファイル |
-| 依存関係 | なし | `blockedBy` 依存グラフ |
-| 永続性 | 会話終了で消失 | セッション横断 |
-| マルチ Agent | なし | `owner` フィールド |
-| ステータス | checked / unchecked | pending → in_progress → completed |
+| 位置づけ | 現在のタスクの実行チェックリスト | 復旧可能なタスクシステム |
+| ストレージ | プロセス内 / セッション状態 | `.tasks/{id}.json` |
+| 依存関係 | なし | `blockedBy` / `blocks` グラフ |
+| ライフサイクル | 現在のセッション / 現在のタスク | セッション横断 |
+| 分担 | タスク認識を扱わない | `owner` / claim |
+| ステータス | pending / in_progress / completed | pending / in_progress / completed |
+| 粒度 | Agent 自身の手順 | 認識・追跡・アンロックできるタスク |
 
 ---