aiterm-mcp 0.22.0 → 0.23.1

package/README.ja.md

@@ -18,7 +18,7 @@
 
 > **あなたの AI に、ほかの AI を操らせる。** 任意の MCP クライアントから 1 回の呼び出しで、コーディングエージェント（Claude・Codex・Grok・Composer）を永続端末の中に起動し、操作用のセッションを手渡す。何をしているかをトークン削減して読み、次の指示を送る。
 >
-> **これは何か:** AI が握る 1 本の永続 MCP 端末——その中に他のコーディングエージェントも起動できる。`ssh`・`docker exec`・REPL・別エージェントの TUI は、すべてその 1 本の端末の中へ「送るだけのテキスト」として入れ子になる。仕組みはあえて素朴——MCP クライアントが相手エージェントの端末を 1 ターンずつ操作するだけ。隠れたプロトコルも・共有メモリも・自律的な交渉も無い。
+> **これは何か:** AI が握る 1 本の永続 MCP 端末——その中に他のコーディングエージェントも起動できる。`ssh`・`docker exec`・REPL・別エージェントの TUI は、すべてその 1 本の端末の中へ「送るだけのテキスト」として入れ子になる。仕組みはあえて素朴——MCP クライアントが相手エージェントの端末を 1 ターンずつ操作するだけ。隠れたプロトコルも・aiterm独自の共有メモリ層も・自律的な交渉も無い。起動したagentは、直接CLIと同じproject／vendorの通常memory・設定を読む。
 >
 > **人が tmux に張り付く必要はない。** aiterm は MCP 越しにプログラムから駆動されるので、「AI が別のエージェントを起動して操作する」のに端末の前に誰も座らなくていい——オーケストレーションのループ・CI ステップ・cron から動かせる。
 >
@@ -96,6 +96,12 @@ host統合は、kitepon.devの製品開発を支える内部基盤
 
 13 ツール: 6 つの **PTY ツール**（`pty_open` / `pty_send` / `pty_read` / `pty_key` / `pty_close` / `pty_list`）で 1 本の永続端末を開き・操作し・読む。加えて 4 つの **エージェント起動ツール**（`claude_agent` / `codex_agent` / `grok_agent` / `composer_agent`）が別のコーディングエージェントの TUI を新しい端末の中に起動し、`claude_turn`がdurable caller向けの構造化issue／recoveryを、`claude_approval`が相関済みClaude承認UI中継を、`diagnostics`が安全なfactory readinessを返す。バックエンドは **tmux** なので、MCP サーバや AI クライアントが再起動してもセッションは生き残る。
 
+**v0.23.0では、ローカル完結の別vendor向けportable forkを追加した。** どのlauncherでも
+`throughline_source_session`と新しいミッションを`prompt`へ渡すと、PTY作成前にローカルの
+Throughlineから対象sessionの読み取り専用handoff contextを取得する。返された記憶はそのまま
+ミッションの前へ置かれ、元sessionのDB所属は移動もcopyもされない。Throughlineが無い、または
+結果が不正／空ならclean launchへfallbackせず明示失敗する。引数を省略した通常起動は従来どおり。
+
 **v0.22.0では4 launcherを完全なプロジェクト共同作業員へ戻した。** 直接CLIを起動した時と同じ
 `HOME`、作業tree、vendor home、project/user/local設定、MCP、plugin、skill、permission、trust、memory、
 session historyをそのまま使う。aitermがlaunchごとに分離するのは完了相関stateだけ。子には
@@ -167,13 +173,19 @@ $ aiterm-wait --session codex1 --cursor <event_cursor>   # exit 0=done / 3=timeo
 
 | ツール | 起動するもの | 主な引数 |
 | --- | --- | --- |
-| `claude_agent` | Claude Code CLI（Anthropic） | `prompt?`, `model?`, `reasoning_effort?`（`low`/`medium`/`high`/`xhigh`/`max`）, `cwd?`, `session_name?` |
-| `codex_agent` | Codex CLI（OpenAI・端末設定／CLI既定、`model?`で上書き） | `prompt?`, `model?`, `reasoning_effort?`（`low`/`medium`/`high`/`xhigh`/`max`/`ultra`）, `cwd?`, `session_name?`, `write_scope?` |
-| `grok_agent` | Grok Build（xAI、既定`grok-4.5`、`model?`で上書き） | `prompt?`, `model?`, `reasoning_effort?`は非対応（指定時は明示エラー）, `cwd?`, `session_name?`, `write_scope?` |
-| `composer_agent` | Grok Build（xAI、既定`grok-composer-2.5-fast`、`model?`で上書き） | `prompt?`, `model?`, `reasoning_effort?`は非対応（指定時は明示エラー）, `cwd?`, `session_name?`, `write_scope?` |
+| `claude_agent` | Claude Code CLI（Anthropic） | `prompt?`, `throughline_source_session?`, `model?`, `reasoning_effort?`（`low`/`medium`/`high`/`xhigh`/`max`）, `cwd?`, `session_name?` |
+| `codex_agent` | Codex CLI（OpenAI・端末設定／CLI既定、`model?`で上書き） | `prompt?`, `throughline_source_session?`, `model?`, `reasoning_effort?`（`low`/`medium`/`high`/`xhigh`/`max`/`ultra`）, `cwd?`, `session_name?`, `write_scope?` |
+| `grok_agent` | Grok Build（xAI、既定`grok-4.5`、`model?`で上書き） | `prompt?`, `throughline_source_session?`, `model?`, `reasoning_effort?`は非対応（指定時は明示エラー）, `cwd?`, `session_name?`, `write_scope?` |
+| `composer_agent` | Grok Build（xAI、既定`grok-composer-2.5-fast`、`model?`で上書き） | `prompt?`, `throughline_source_session?`, `model?`, `reasoning_effort?`は非対応（指定時は明示エラー）, `cwd?`, `session_name?`, `write_scope?` |
 
 各ベンダーのCLIが導入・認証済みであること。CLI不在・不正なmodel/effort・実在しない`cwd`はsession作成前に失敗し、残骸を残さない。ClaudeはさらにPTY作成前に同じCLIの`auth status --json`が`loggedIn:true`を返すことを要求する。4 launcherは通常のvendor credential/config storeをその場で使い、fake `HOME`、private `CODEX_HOME`/`GROK_HOME`、project/user config snapshotを作らない。Claudeだけは完了相関用Stop hook settingsを通常の`user,project,local` settingsへ加算する。Grok/Composerは画面入力欄だけでなく通常sessionの`mcp_init_completed` eventも確認してから送信し、共有MCP初期化中の早送信を防ぐ。相関付きClaudeのactive turn中はC-c以外の`pty_key`と素送信を拒否し、承認UIは`claude_approval`で単発Yes/Noだけを相関付きで中継する。
 
+portable forkは任意である。`throughline_source_session`を使う場合、`prompt`は必須の新ミッションとなり、
+`launch_operation_id`とは併用できない。aitermは`THROUGHLINE_BIN`、次に`PATH`からThroughlineを解決し、
+`throughline handoff-context --session <id> --json`のcontextを固定区切りとミッションの前へそのまま置く。
+この経路だけ`throughline >= 0.9.0`が必要で、元sessionのDB所属は変わらない。引数省略時には
+Throughline自体が不要である。
+
 エージェント間の隠れたプロトコルは無い。起動したClaude/Codex/Grok/Composerは利用者がattachできるもう1本の永続sessionであり、MCPクライアントが通常のPTY操作で駆動する。
 
 ## デモ
@@ -369,13 +381,18 @@ consumer は `aiterm-runtime-errors snapshot` を読み、durable ingestion 後
 
 | ツール | 起動するもの | 主な引数 |
 | --- | --- | --- |
-| `claude_agent` | Claude Code CLI（Anthropic） | `prompt?`, `model?`, `reasoning_effort?`（`low`/`medium`/`high`/`xhigh`/`max`）, `cwd?`, `session_name?` |
-| `codex_agent` | Codex CLI（OpenAI・端末設定／CLI既定、`model?`で上書き） | `prompt?`, `model?`, `reasoning_effort?`（`low`/`medium`/`high`/`xhigh`/`max`/`ultra`）, `cwd?`, `session_name?`, `write_scope?` |
-| `grok_agent` | Grok Build（xAI、既定`grok-4.5`、`model?`で上書き） | `prompt?`, `model?`, `reasoning_effort?`は非対応（指定時は明示エラー）, `cwd?`, `session_name?`, `write_scope?` |
-| `composer_agent` | Grok Build（xAI、既定`grok-composer-2.5-fast`、`model?`で上書き） | `prompt?`, `model?`, `reasoning_effort?`は非対応（指定時は明示エラー）, `cwd?`, `session_name?`, `write_scope?` |
+| `claude_agent` | Claude Code CLI（Anthropic） | `prompt?`, `throughline_source_session?`, `model?`, `reasoning_effort?`（`low`/`medium`/`high`/`xhigh`/`max`）, `cwd?`, `session_name?` |
+| `codex_agent` | Codex CLI（OpenAI・端末設定／CLI既定、`model?`で上書き） | `prompt?`, `throughline_source_session?`, `model?`, `reasoning_effort?`（`low`/`medium`/`high`/`xhigh`/`max`/`ultra`）, `cwd?`, `session_name?`, `write_scope?` |
+| `grok_agent` | Grok Build（xAI、既定`grok-4.5`、`model?`で上書き） | `prompt?`, `throughline_source_session?`, `model?`, `reasoning_effort?`は非対応（指定時は明示エラー）, `cwd?`, `session_name?`, `write_scope?` |
+| `composer_agent` | Grok Build（xAI、既定`grok-composer-2.5-fast`、`model?`で上書き） | `prompt?`, `throughline_source_session?`, `model?`, `reasoning_effort?`は非対応（指定時は明示エラー）, `cwd?`, `session_name?`, `write_scope?` |
 
 対応するCLI（`claude` / `codex` / `grok`）の導入・認証が必要。前提違反はsession作成前に明示失敗する。4 launcherすべてが通常project/user環境と同じ非ブロックdispatch契約を使う。Claude／Codex／Grok／Composerのdepth 1 live smokeと、Claude親→Claude孫のdepth 2 nested delegation smokeはgreenであり、fixtureによる検証とは区別して記録する。
 
+`throughline_source_session`と空でない新ミッション`prompt`を指定すると、Throughlineの読み取り専用
+handoff contextを前置きできる。この任意経路は`throughline >= 0.9.0`を必要とし、
+`launch_operation_id`とは併用不可で、元sessionのDB所属を変更しない。Throughlineは
+`THROUGHLINE_BIN`、次に`PATH`から解決し、不在・不正・空のexportはPTY作成前に明示失敗する。
+
 エージェントの回答が画面 tailより長ければ、対話callerは`pty_read({ agent_transcript:true })`で再promptなしに全文回収する。Claudeはlaunch相関付きStop hookのowner-only resultを検証し、private transcriptを読まない。Codexは通常rollout transcript、Grok/Composerは通常session historyから同じturnを回収する。不在・非agent・抽出不能は明示エラー。
 
 ### 完了検出（5 層）
@@ -404,7 +421,7 @@ consumer は `aiterm-runtime-errors snapshot` を読み、durable ingestion 後
 - **tmux**（実行時の前提。`tmux -V` で確認。未導入なら `apt install tmux` / `brew install tmux`）
   - **macOS / Linux / WSL2** は tmux を直接使う。macOS は同梱されないので `brew install tmux` で導入する。MCP クライアントがターミナルでなく **GUI から起動**された場合、Homebrew の bin（Apple Silicon: `/opt/homebrew/bin`、Intel: `/usr/local/bin`）が `PATH` に入らないことがある。その場合 aiterm が自動で探索するか、**`AITERM_TMUX=/path/to/tmux`** で明示指定する。
   - **Windows ネイティブ**には tmux が無いため、aiterm は裏で **WSL の中の tmux** を透過的に使う。[WSL](https://learn.microsoft.com/ja-jp/windows/wsl/) を導入・初期化し、**WSL のディストリ内に tmux を入れる**こと（`sudo apt install tmux`）。`wsl tmux -V` で確認できる。セッション・ソケット・人の `attach` はすべて WSL 側にあり、AI は Windows 側のコマンドから操作するだけ。（Windows のツールは SSH と同じく入れ子で握る: `pty_send "powershell.exe …"` で PowerShell に入る。）
-- **エージェント起動ツール**を使う場合: 対応するベンダー CLI が導入・認証済みであること——`claude_agent` は `claude`、`codex_agent` は `codex`、`grok_agent` / `composer_agent` は `grok`。（PTY ツールだけ使うなら不要。）
+- **エージェント起動ツール**を使う場合: 対応するベンダー CLI が導入・認証済みであること——`claude_agent` は `claude`、`codex_agent` は `codex`、`grok_agent` / `composer_agent` は `grok`。portable forkだけは追加で`throughline >= 0.9.0`が必要だが、通常のclean launchには不要。（PTY ツールだけ使うなら不要。）
 - 任意: [`rtk`](https://github.com/rtk-ai/rtk) バイナリ（`pty_send` の `rtk: true` 委譲で使う。無くても動く）
 
 ## 既知の制約（バグではなく仕様）

package/README.md

@@ -18,7 +18,7 @@
 
 > **Let your AI orchestrate other AIs.** From any MCP client, one call spawns a coding agent (Claude, Codex, Grok, or Composer) inside a persistent terminal and hands you a session to drive: read what it's doing token-reduced, send it the next instruction.
 >
-> **What it is:** one persistent MCP terminal your AI drives — and can launch other coding agents into. `ssh`, `docker exec`, a REPL, or another agent's TUI all nest inside that one terminal as just text you send in. The mechanism is deliberately plain — your MCP client drives the other agent's terminal turn by turn: no hidden protocol, no shared memory, no autonomous negotiation.
+> **What it is:** one persistent MCP terminal your AI drives — and can launch other coding agents into. `ssh`, `docker exec`, a REPL, or another agent's TUI all nest inside that one terminal as just text you send in. The mechanism is deliberately plain — your MCP client drives the other agent's terminal turn by turn: no hidden protocol, no separate aiterm-owned shared-memory layer, no autonomous negotiation. Launched agents still read the normal project and vendor memory/configuration that a direct CLI launch would use.
 >
 > **No human at a tmux required.** aiterm is driven programmatically over MCP, so an AI can launch and drive another agent with no one sitting in the terminal — from an orchestration loop, a CI step, or a cron job.
 >
@@ -96,6 +96,13 @@ toolchain behind kitepon.dev's products.
 
 Thirteen tools: six **PTY tools** — `pty_open` / `pty_send` / `pty_read` / `pty_key` / `pty_close` / `pty_list` — to open, drive, and read one persistent terminal, four **agent launchers** — `claude_agent` / `codex_agent` / `grok_agent` / `composer_agent` — that each start another coding agent's TUI inside a fresh one, `claude_turn` for durable structured issue/recovery, `claude_approval` for correlated Claude approval prompts, and `diagnostics` for safe factory readiness. The backend is **tmux**, so sessions survive even if the MCP server or the AI client restarts.
 
+**v0.23.0 adds a local, cross-vendor portable fork.** Pass `throughline_source_session`
+with a mission in `prompt` to any launcher, and aiterm asks the locally installed Throughline
+for that session's read-only handoff context before creating the PTY. The exact returned memory
+is prepended to the mission without moving or copying the source session's database ownership.
+If Throughline is missing or returns an invalid/empty result, launch fails visibly with no clean
+fallback. Omitting the field preserves the ordinary clean launch.
+
 **v0.22.0 makes launched agents full project collaborators.** All four launchers now use the
 same normal `HOME`, working tree, vendor home, project/user/local configuration, MCP servers,
 plugins, skills, permissions, trust, memory, and session history as a direct CLI launch. Aiterm
@@ -185,13 +192,20 @@ One call per model, so the tool name itself tells you which model you get:
 
 | Tool | Launches | Key args |
 | --- | --- | --- |
-| `claude_agent` | Claude Code CLI (Anthropic) | `prompt?`, `model?`, `reasoning_effort?` (`low`/`medium`/`high`/`xhigh`/`max`), `cwd?`, `session_name?`, `launch_operation_id?` |
-| `codex_agent` | Codex CLI (OpenAI; terminal config/CLI default unless overridden) | `prompt?`, `model?`, `reasoning_effort?` (`low`/`medium`/`high`/`xhigh`/`max`/`ultra`; ultra enables proactive automatic delegation), `cwd?`, `session_name?`, `write_scope?` |
-| `grok_agent` | Grok Build, model `grok-4.5` by default (`model?` overrides) (xAI) | `prompt?`, `model?`, `reasoning_effort?` unsupported (an explicit value is an error; Grok CLI `--effort` is headless-only), `cwd?`, `session_name?`, `write_scope?` |
-| `composer_agent` | Grok Build, model `grok-composer-2.5-fast` by default (`model?` overrides) (xAI) | `prompt?`, `model?`, `reasoning_effort?` unsupported (an explicit value is an error), `cwd?`, `session_name?`, `write_scope?` |
+| `claude_agent` | Claude Code CLI (Anthropic) | `prompt?`, `throughline_source_session?`, `model?`, `reasoning_effort?` (`low`/`medium`/`high`/`xhigh`/`max`), `cwd?`, `session_name?`, `launch_operation_id?` |
+| `codex_agent` | Codex CLI (OpenAI; terminal config/CLI default unless overridden) | `prompt?`, `throughline_source_session?`, `model?`, `reasoning_effort?` (`low`/`medium`/`high`/`xhigh`/`max`/`ultra`; ultra enables proactive automatic delegation), `cwd?`, `session_name?`, `write_scope?` |
+| `grok_agent` | Grok Build, model `grok-4.5` by default (`model?` overrides) (xAI) | `prompt?`, `throughline_source_session?`, `model?`, `reasoning_effort?` unsupported (an explicit value is an error; Grok CLI `--effort` is headless-only), `cwd?`, `session_name?`, `write_scope?` |
+| `composer_agent` | Grok Build, model `grok-composer-2.5-fast` by default (`model?` overrides) (xAI) | `prompt?`, `throughline_source_session?`, `model?`, `reasoning_effort?` unsupported (an explicit value is an error), `cwd?`, `session_name?`, `write_scope?` |
 
 The vendor CLI must be installed and authenticated (`claude` for `claude_agent`; `codex` for `codex_agent`; `grok` for both Grok tools). aiterm resolves the binary via `CLAUDE_BIN` / `CODEX_BIN` / `GROK_BIN`, then each documented default location, then `PATH`. Prerequisites are checked **before** a session exists: empty `model` values and unsupported effort values are rejected up front; a missing CLI binary or a nonexistent `cwd` fails for all four. Before creating a Claude session, aiterm also requires a successful structured `claude auth status --json` result with `loggedIn: true`; unavailable, malformed, or failed authentication leaves **zero leftover session**. All launchers use the normal vendor-owned credential and configuration stores in place. No launcher creates a fake `HOME`, a private `CODEX_HOME`/`GROK_HOME`, or a snapshot of project/user configuration.
 
+Portable fork is optional. When `throughline_source_session` is present, `prompt` is the required
+new mission and `launch_operation_id` cannot be combined with it. aiterm resolves Throughline via
+`THROUGHLINE_BIN` and then `PATH`, runs `throughline handoff-context --session <id> --json`, and
+places its returned context before a fixed separator and the mission. This route requires
+`throughline >= 0.9.0`; it reads the source memory without changing that database's session
+ownership. No Throughline dependency is needed when the field is omitted.
+
 Claude and Codex launchers forward `model` and `reasoning_effort` through public CLI flags; Grok/Composer reject `reasoning_effort` because it is headless-only. Pass an absolute path for `cwd` — `~` is not expanded. Durable callers can make a promptless Claude launch exactly replayable by passing an explicit `session_name` and `launch_operation_id`. Claude adds a launch-local settings file only for the correlated Stop hook and loads it together with normal `user,project,local` setting sources; it does not replace normal hooks, MCPs, plugins, permissions, or trust state. The hook event contains no answer body, and the bounded owner-only result is returned by `pty_read({ agent_transcript:true })` without reading Claude's private transcript. While a correlated Claude turn is active, raw sends and non-interrupt keys are rejected. Exact `/login` and `/logout` dispatches are rejected so shared authentication is repaired once in a normal terminal. Codex reads its normal rollout store; Grok/Composer read their normal session event/history files. Before dispatch, Codex waits for an idle TUI, while Grok/Composer additionally require the vendor's structured `mcp_init_completed` event so a visible input box cannot accept a prompt too early. Correlated completion requires POSIX filesystem semantics (Linux, WSL2, macOS).
 
 There is no hidden protocol between agents: a launched Claude, Codex, Grok, or Composer is another user-visible persistent terminal session. The MCP client drives that TUI with ordinary PTY operations, and a human can attach to watch or take over.
@@ -391,13 +405,19 @@ Each launcher starts a specific vendor's interactive coding-agent TUI inside a f
 
 | Tool | Launches | Key args |
 | --- | --- | --- |
-| `claude_agent` | Claude Code CLI (Anthropic) | `prompt?`, `model?`, `reasoning_effort?` (`low`/`medium`/`high`/`xhigh`/`max`), `cwd?`, `session_name?`, `launch_operation_id?` |
-| `codex_agent` | Codex CLI (OpenAI; terminal config/CLI default unless overridden) | `prompt?`, `model?`, `reasoning_effort?` (`low`/`medium`/`high`/`xhigh`/`max`/`ultra`; ultra enables proactive automatic delegation), `cwd?`, `session_name?`, `write_scope?` |
-| `grok_agent` | Grok Build, model `grok-4.5` by default (`model?` overrides) (xAI) | `prompt?`, `model?`, `reasoning_effort?` unsupported (an explicit value is an error; Grok CLI `--effort` is headless-only), `cwd?`, `session_name?`, `write_scope?` |
-| `composer_agent` | Grok Build, model `grok-composer-2.5-fast` by default (`model?` overrides) (xAI) | `prompt?`, `model?`, `reasoning_effort?` unsupported (an explicit value is an error), `cwd?`, `session_name?`, `write_scope?` |
+| `claude_agent` | Claude Code CLI (Anthropic) | `prompt?`, `throughline_source_session?`, `model?`, `reasoning_effort?` (`low`/`medium`/`high`/`xhigh`/`max`), `cwd?`, `session_name?`, `launch_operation_id?` |
+| `codex_agent` | Codex CLI (OpenAI; terminal config/CLI default unless overridden) | `prompt?`, `throughline_source_session?`, `model?`, `reasoning_effort?` (`low`/`medium`/`high`/`xhigh`/`max`/`ultra`; ultra enables proactive automatic delegation), `cwd?`, `session_name?`, `write_scope?` |
+| `grok_agent` | Grok Build, model `grok-4.5` by default (`model?` overrides) (xAI) | `prompt?`, `throughline_source_session?`, `model?`, `reasoning_effort?` unsupported (an explicit value is an error; Grok CLI `--effort` is headless-only), `cwd?`, `session_name?`, `write_scope?` |
+| `composer_agent` | Grok Build, model `grok-composer-2.5-fast` by default (`model?` overrides) (xAI) | `prompt?`, `throughline_source_session?`, `model?`, `reasoning_effort?` unsupported (an explicit value is an error), `cwd?`, `session_name?`, `write_scope?` |
 
 The vendor CLI must be installed and authenticated (`claude` for `claude_agent`; `codex` for `codex_agent`; `grok` for both Grok tools). Binary resolution uses `CLAUDE_BIN` / `CODEX_BIN` / `GROK_BIN`, then each documented default location, then `PATH`. Missing binaries, invalid model/effort values, and nonexistent `cwd` fail before a session is created. Claude additionally requires a structured healthy authentication status before any PTY exists, and correlated Claude sessions reject `/login` and `/logout`; repair authentication once in a normal terminal. All four launchers share the normal project/user environment and the same non-blocking dispatch contract. Claude, Codex, Grok, and Composer depth-1 live smokes and a Claude depth-2 nested-delegation smoke are green; fixture coverage remains a separate claim. Native Windows can launch agents but correlated completion is not supported yet.
 
+Set `throughline_source_session` together with a non-empty mission in `prompt` to prepend
+Throughline's read-only handoff context. This optional route requires `throughline >= 0.9.0`,
+cannot be combined with `launch_operation_id`, and leaves the source session's database ownership
+unchanged. Throughline is resolved through `THROUGHLINE_BIN` and then `PATH`; a missing or invalid
+export fails before the PTY exists instead of silently launching clean.
+
 When an agent's answer is longer than the on-screen tail (pane height ≈ 24 lines), callers recover it in full with `pty_read({ agent_transcript: true })`. It returns the most recently completed turn's final assistant message in plain text with no re-prompting. Claude reads the bounded owner-only result captured by the launch-correlated Stop hook and verifies its digest/byte count; it never reads Claude's private transcript. Durable machine callers should use `claude_turn`: `issue` sends once, `recover` never sends, `pending` is distinct from unsafe or malformed state, and only `completed` carries the exact verified `raw_output`. Codex uses the normal rollout transcript's `task_complete.turn_id`; Grok/Composer use their normal session history after the last real user row. Missing or ambiguous attribution remains an explicit error.
 
 ### Completion detection (5 layers)
@@ -439,7 +459,7 @@ Sessions live on a shared tmux socket. The `tmux -S … attach -t <id>` line pri
 - **tmux** (runtime prerequisite; check with `tmux -V`. Install with `apt install tmux` / `brew install tmux`)
   - **macOS / Linux / WSL2** run tmux directly. On macOS install it with `brew install tmux` (stock macOS ships none). If your MCP client is launched from the **GUI** rather than a terminal, Homebrew's bin (`/opt/homebrew/bin` on Apple Silicon, `/usr/local/bin` on Intel) may be off its `PATH`; aiterm auto-searches those locations, or set **`AITERM_TMUX=/path/to/tmux`** to point at it explicitly.
   - **Native Windows** has no tmux, so aiterm transparently runs tmux **inside WSL**. It needs [WSL](https://learn.microsoft.com/windows/wsl/) installed and initialized, with **tmux installed inside your WSL distro** (`sudo apt install tmux`); verify with `wsl tmux -V`. Sessions, the socket, and human `attach` all live on the WSL side — the AI just drives them from the Windows-side command. (You reach Windows tools the same way you reach SSH: `pty_send "powershell.exe …"` nests into PowerShell.)
-- For the **agent launchers**: the corresponding vendor CLI, installed and authenticated — `claude` for `claude_agent`, `codex` for `codex_agent`, `grok` for `grok_agent` / `composer_agent`. (Not needed if you only use the PTY tools.)
+- For the **agent launchers**: the corresponding vendor CLI, installed and authenticated — `claude` for `claude_agent`, `codex` for `codex_agent`, `grok` for `grok_agent` / `composer_agent`. Portable fork additionally needs `throughline >= 0.9.0`; ordinary clean launch does not. (Not needed if you only use the PTY tools.)
 - Optional: the [`rtk`](https://github.com/rtk-ai/rtk) binary (used by `pty_send`'s `rtk: true` delegation; works fine without it)
 
 ## Known constraints (by design, not bugs)

package/dist/core.js

@@ -342,9 +342,14 @@ function assertSessionName(name) {
         throw new AitermError(`session 名は英数字と _ - のみ・64文字以内にしてください: ${JSON.stringify(name)}`, 2);
 }
 function currentUid() {
-    if (typeof process.getuid !== "function") {
-        throw new AitermError("agent_done は POSIX/macOS/Linux のみ対応です（native Windows は未対応）", 2);
-    }
+    // Windows(native)は process.getuid を持たない。以前はここで throw していたが、
+    // agent metadata の存在確認経由で素の pty_send まで巻き込んで全 send を殺していた。
+    // Windows の fs.Stats.uid は常に 0 なので、ここも 0 を返せば owner 比較
+    // (st.uid !== currentUid()) は自然に通過する。Windows は POSIX owner 検証を
+    // 持たない（NTFS ACL は別体系）という既知の制約の明示的受容であり、POSIX 側は
+    // getuid をそのまま返すため挙動不変。
+    if (typeof process.getuid !== "function")
+        return 0;
     return process.getuid();
 }
 function runtimeStateBase() {
@@ -3752,6 +3757,71 @@ function isUsableExecutableFile(candidate) {
         return false;
     }
 }
+const THROUGHLINE_HANDOFF_CONTEXT_SCHEMA = "throughline.handoff_context.v1";
+const PORTABLE_FORK_MISSION_SEPARATOR = "\n\n---\n\n## Portable fork mission\n\n";
+function resolveThroughlineBin() {
+    const fromEnv = process.env.THROUGHLINE_BIN;
+    if (fromEnv)
+        return isUsableExecutableFile(fromEnv) ? fromEnv : null;
+    const resolved = spawnSync(isWin ? "where" : "which", ["throughline"], {
+        encoding: "utf8",
+    }).stdout?.split(/\r?\n/).find(Boolean) ?? null;
+    return resolved && isUsableExecutableFile(resolved) ? resolved : null;
+}
+function runThroughlineHandoffContext(bin, sessionId) {
+    if (isWin && /\.(?:cmd|bat)$/i.test(bin)) {
+        const ps1 = path.join(path.dirname(bin), `${path.basename(bin, path.extname(bin))}.ps1`);
+        if (fs.existsSync(ps1)) {
+            return spawnSync("powershell.exe", [
+                "-NoLogo",
+                "-NoProfile",
+                "-NonInteractive",
+                "-ExecutionPolicy",
+                "Bypass",
+                "-File",
+                ps1,
+                "handoff-context",
+                "--session",
+                sessionId,
+                "--json",
+            ], { encoding: "utf8" });
+        }
+    }
+    return spawnSync(bin, ["handoff-context", "--session", sessionId, "--json"], {
+        encoding: "utf8",
+    });
+}
+export function composePortableForkPrompt(context, mission) {
+    return context + PORTABLE_FORK_MISSION_SEPARATOR + mission;
+}
+function portableForkPrompt(sourceSessionId, mission) {
+    const bin = resolveThroughlineBin();
+    if (!bin) {
+        throw new AitermError("Throughline CLIが見つかりません。portable forkのsessionは作成していません", 2);
+    }
+    const result = runThroughlineHandoffContext(bin, sourceSessionId);
+    if (result.error || result.status !== 0) {
+        throw new AitermError("Throughline handoff-contextの取得に失敗しました。portable forkのsessionは作成していません", 2);
+    }
+    let value;
+    try {
+        value = JSON.parse(result.stdout ?? "");
+    }
+    catch {
+        value = null;
+    }
+    if (value === null ||
+        typeof value !== "object" ||
+        Array.isArray(value) ||
+        value.schema !== THROUGHLINE_HANDOFF_CONTEXT_SCHEMA ||
+        value.status !== "ready" ||
+        value.sessionId !== sourceSessionId ||
+        typeof value.context !== "string" ||
+        !value.context.trim()) {
+        throw new AitermError("Throughline handoff-contextの応答が不正です。portable forkのsessionは作成していません", 2);
+    }
+    return composePortableForkPrompt(value.context, mission);
+}
 /** vendor CLI の存在だけを安全に要約する。認証状態・実行出力・解決先 path は返さない。 */
 export function vendorLauncherDiagnostic(kind) {
     try {
@@ -4083,7 +4153,20 @@ export function openAgent(kind, opts = {}) {
     ];
 }
 export async function openAgentWithInitialPrompt(kind, opts = {}) {
-    const prompt = opts.prompt ?? null;
+    const mission = opts.prompt ?? null;
+    const sourceSessionId = opts.throughline_source_session ?? null;
+    if (sourceSessionId !== null && !sourceSessionId.length) {
+        throw new AitermError("throughline_source_sessionが空文字です", 2);
+    }
+    if (sourceSessionId !== null && (mission === null || !mission.trim())) {
+        throw new AitermError("throughline_source_session指定時はpromptにmissionが必要です", 2);
+    }
+    if (sourceSessionId !== null && opts.launch_operation_id != null) {
+        throw new AitermError("throughline_source_sessionはlaunch_operation_idと併用できません", 2);
+    }
+    const prompt = sourceSessionId === null
+        ? mission
+        : portableForkPrompt(sourceSessionId, mission);
     if (opts.launch_operation_id != null && prompt !== null) {
         throw new AitermError("launch_operation_idはpromptなしのClaude相関launchだけで指定できます", 2);
     }

package/dist/index.js

@@ -447,6 +447,11 @@ function registerAgentTool(toolName, kind, desc) {
         description: desc,
         inputSchema: {
             prompt: z.string().nullish().describe("起動時に渡す初手プロンプト（任意）。送信後は待たずに即返る"),
+            throughline_source_session: z
+                .string()
+                .min(1)
+                .optional()
+                .describe("同一端末のThroughline sessionから所有権を変えずに記憶を読み、promptのmissionより前へ注入する"),
             model: z.string().nullish().describe(agentModelDesc(kind)),
             // grok/composer の effort は対話 TUI で無効（headless 専用）＝core 側が起動前に明示エラーで拒否。
             // codex は CLI 側の値集合が版で変わるため縛らない（core 側も同方針）。
@@ -470,10 +475,11 @@ function registerAgentTool(toolName, kind, desc) {
             submit_residue: z.boolean().nullable(),
             ...writeScopeOutputSchema,
         },
-    }, async ({ prompt, model, reasoning_effort, cwd, session_name, launch_operation_id, write_scope }) => {
+    }, async ({ prompt, throughline_source_session, model, reasoning_effort, cwd, session_name, launch_operation_id, write_scope }) => {
         try {
             const [sid, hint, eventCursor, submitResidue] = await core.openAgentWithInitialPrompt(kind, {
                 prompt: prompt ?? undefined,
+                throughline_source_session,
                 model: model ?? undefined,
                 reasoning_effort: reasoning_effort ?? undefined,
                 cwd: cwd ?? undefined,

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "aiterm-mcp",
-  "version": "0.22.0",
+  "version": "0.23.1",
   "mcpName": "io.github.kitepon-rgb/aiterm-mcp",
   "description": "Persistent tmux terminal MCP that lets Claude Code drive Codex CLI's interactive TUI, including slash commands and $imagegen. Also runs durable PTY sessions for SSH, containers, REPLs, and coding agents.",
   "keywords": [