aiterm-mcp 0.40.3 → 0.41.0

package/CHANGELOG.md

@@ -7,6 +7,12 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [0.41.0] - 2026-09-27
+
+### 削除
+
+- 旧互換alias `composer_agent` と、agent種別の`composer`を削除した。ComposerはCursorのmodelの一つで、現行のGrok CLIにはComposerが無いため、このaliasは常にcatalogエラーで起動できなかった。Composerは`agent_launch(harness=cursor-cli, model=composer-2.5-fast)`で起動する。`provider`／`vendor`の列挙から`composer`を外し、Claudeの親hookのmatcherからも`composer_agent`を外した。
+
 ## [0.40.3] - 2026-09-27
 
 ### 文書
@@ -1804,7 +1810,8 @@ prototype (preserved under `prototype/python/` as the porting source and referen
   `ubuntu-latest` for Node 18/20/22, publishing to npm on `v*` tags with
   provenance.
 
-[Unreleased]: https://github.com/kitepon/aiterm-mcp/compare/v0.40.3...HEAD
+[Unreleased]: https://github.com/kitepon/aiterm-mcp/compare/v0.41.0...HEAD
+[0.41.0]: https://github.com/kitepon/aiterm-mcp/compare/v0.40.3...v0.41.0
 [0.40.3]: https://github.com/kitepon/aiterm-mcp/compare/v0.40.2...v0.40.3
 [0.40.2]: https://github.com/kitepon/aiterm-mcp/compare/v0.40.1...v0.40.2
 [0.40.1]: https://github.com/kitepon/aiterm-mcp/compare/v0.40.0...v0.40.1

package/README.ja.md

@@ -143,9 +143,9 @@ diagnostics、recovery、update、releaseを所有します。このREADMEと[
 
 **言葉でなく実測で:** 記録済み203テストのベンチマークでは、`pty_read` はコンテキストに載るトークンを生ログの **約 7.1 分の 1** に減らす。しかも pass/fail の判定は畳んでも残る。→ [組み込みシェルツールとの使い分け](#組み込みシェルツールとの使い分け)
 
-17ツール: 7つのPTYツール、正規のagent起動入口`agent_launch`、移行用の旧4alias、`agent_configure`、`agent_approval`、`claude_turn`、`claude_approval`、`diagnostics`。backendはPOSIXのtmux／Windows nativeのpsmuxなので、MCPサーバやAIクライアントが再起動してもsessionは生き残る。
+16ツール: 7つのPTYツール、正規のagent起動入口`agent_launch`、移行用の旧3alias、`agent_configure`、`agent_approval`、`claude_turn`、`claude_approval`、`diagnostics`。backendはPOSIXのtmux／Windows nativeのpsmuxなので、MCPサーバやAIクライアントが再起動してもsessionは生き残る。
 
-**v0.28.0では実行基盤harnessとmodelを分離した。** harnessはagent loop・認証・hook・session・transcriptを所有し、modelはその上で選ぶ。Cursor Agent CLIでGPT／Claude／Grokを選んでも完了契約はCursor方式のまま。ComposerはCursorのmodelの一つで、harnessでもGrokのmodelでもない。`harness:"cursor-cli", model:"composer-2.5-fast"`（または`composer-2.5`）で表す。旧4起動ツールは同じ実装へ流れる互換alias。
+**v0.28.0では実行基盤harnessとmodelを分離した。** harnessはagent loop・認証・hook・session・transcriptを所有し、modelはその上で選ぶ。Cursor Agent CLIでGPT／Claude／Grokを選んでも完了契約はCursor方式のまま。ComposerはCursorのmodelの一つで、harnessでもGrokのmodelでもない。`harness:"cursor-cli", model:"composer-2.5-fast"`（または`composer-2.5`）で表す。旧起動ツールは同じ実装へ流れる互換alias。
 
 **v0.25.2ではGrok 4.6を含む同一sessionの連続設定変更を安定化。** Grok Build 1.0.3で
 `/model`の成功通知が再描画により消えても、変更前には無かった要求model／effortが常駐footerへ現れた
@@ -203,7 +203,7 @@ runtime-error store は canonical dotagents config の `collection.enabled: true
 場合だけ収集し、既定OFF、network送信は行いません。tag起点CIのnpm provenance（OIDC Trusted
 Publishing）で公開し、GitHub Release が Official MCP Registry を再登録します。
 
-**状態:** 開発継続中 · 現行公開版 **v0.40.3** · 動作対象は Linux · WSL2 · macOS · Windows ネイティブ · MIT · [変更履歴](CHANGELOG.md)。
+**状態:** 開発継続中 · 現行公開版 **v0.41.0** · 動作対象は Linux · WSL2 · macOS · Windows ネイティブ · MIT · [変更履歴](CHANGELOG.md)。
 
 ### 更新と巻き戻し
 
@@ -406,7 +406,7 @@ MCP クライアントが aiterm を stdio 越しにプログラムから駆動
 
 ```mermaid
 flowchart LR
-    AI["AI / MCP client<br/>(the orchestrator)"] -->|"pty_send · pty_observe · agent_launch · agent_configure · agent_approval · claude_turn · claude_approval<br/>旧launcher alias · diagnostics"| S["aiterm-mcp<br/>stdio MCP · 17 tools"]
+    AI["AI / MCP client<br/>(the orchestrator)"] -->|"pty_send · pty_observe · agent_launch · agent_configure · agent_approval · claude_turn · claude_approval<br/>旧launcher alias · diagnostics"| S["aiterm-mcp<br/>stdio MCP · 16 tools"]
     S -->|"pty_read<br/>token-reduced"| AI
     S -->|"tmux / psmux<br/>send · capture"| P["persistent PTYs<br/>再起動を跨ぐ"]
     P -->|"ssh · docker · repl"| R["nested<br/>remote · container · REPL"]
@@ -523,7 +523,7 @@ Claudeの相関済み承認は既存の`claude_approval`を使う。
 | `pty_observe` | pane／harnessの生存、native process identity、状態と活動 | `session_id`, `cursor?` |
 | `agent_launch` | harnessとmodelを別軸で選ぶ正規agent起動入口 | `harness`, `prompt?`, `model?`, `reasoning_effort?`, `cwd?`, `write_scope?`, `trust_project?`, `env_vars?`, `throughline_source_session?`, `throughline_supplement_file?` |
 | `agent_approval` | Codexの現在の承認を検査し、単発許可・拒否を送る | `action`, `session_id`, `approval_choice?`, `observed_prompt_digest?` |
-| `claude_agent` / `codex_agent` / `grok_agent` / `composer_agent` | deprecated互換alias（`composer_agent`は旧Grok CLI presetで今は起動できない。Composerは`agent_launch`の`cursor-cli`で使う） | 旧launcher引数 |
+| `claude_agent` / `codex_agent` / `grok_agent` | deprecated互換alias（`composer_agent`は0.41.0で削除。Composerは`agent_launch`の`cursor-cli`で使う） | 旧launcher引数 |
 | `agent_configure` | 起動中のClaude／Codex／Grok／Cursorを再起動せずmodel／effort変更 | `session_id`, `model?`, `reasoning_effort?` |
 | `claude_turn` | 相関済みClaude operationをdispatch（issue）または回収（recover） | `action`, `session_id`, `operation_id`, `text?` |
 | `claude_approval` | 現在表示中の相関済みClaude承認UIを検査または応答 | `action`, `session_id`, `operation_id?`, `approval_choice?`, `observed_prompt_digest?` |

package/README.md

@@ -145,9 +145,9 @@ Aiterm and is not a runtime dependency.
 
 **Measured, not claimed:** in the recorded 203-test benchmark, a `pty_read` puts **~7.1× fewer tokens** in your context than the raw log — and the pass/fail verdict survives the fold. → [When to reach for it vs. the built-in shell](#when-to-reach-for-it-vs-the-built-in-shell)
 
-Seventeen tools: seven **PTY tools** — `pty_open` / `pty_send` / `pty_read` / `pty_key` / `pty_close` / `pty_list` / `pty_observe` — to open, drive, read, and observe one persistent terminal; one canonical **agent launcher**, `agent_launch`, which selects `claude-code`, `codex-cli`, `grok-cli`, or `cursor-cli` as the execution harness; four deprecated launcher aliases kept for migration; `agent_configure`; `agent_approval`; `claude_turn`; `claude_approval`; and `diagnostics`. The backend is **tmux on POSIX and psmux on native Windows**, so sessions survive even if the MCP server or the AI client restarts.
+Sixteen tools: seven **PTY tools** — `pty_open` / `pty_send` / `pty_read` / `pty_key` / `pty_close` / `pty_list` / `pty_observe` — to open, drive, read, and observe one persistent terminal; one canonical **agent launcher**, `agent_launch`, which selects `claude-code`, `codex-cli`, `grok-cli`, or `cursor-cli` as the execution harness; three deprecated launcher aliases kept for migration; `agent_configure`; `agent_approval`; `claude_turn`; `claude_approval`; and `diagnostics`. The backend is **tmux on POSIX and psmux on native Windows**, so sessions survive even if the MCP server or the AI client restarts.
 
-**v0.28.0 separates the execution harness from the model.** The harness owns the agent loop, authentication, hooks, session, and transcript; `model` is what that harness runs. Cursor Agent CLI can therefore select GPT, Claude, or Grok without changing the completion contract from Cursor hooks to another harness's. Composer is one of Cursor's models, not a harness and not a Grok model: use `harness: "cursor-cli", model: "composer-2.5-fast"` (or `composer-2.5`). The old four launcher tools are thin compatibility aliases over the same implementation.
+**v0.28.0 separates the execution harness from the model.** The harness owns the agent loop, authentication, hooks, session, and transcript; `model` is what that harness runs. Cursor Agent CLI can therefore select GPT, Claude, or Grok without changing the completion contract from Cursor hooks to another harness's. Composer is one of Cursor's models, not a harness and not a Grok model: use `harness: "cursor-cli", model: "composer-2.5-fast"` (or `composer-2.5`). The old launcher tools are thin compatibility aliases over the same implementation.
 
 **v0.25.2 stabilizes repeated in-place configuration changes, including Grok 4.6.** If Grok Build
 1.0.3 redraws before its `/model` success notice can be observed, aiterm confirms the requested model/effort
@@ -217,7 +217,7 @@ collection is off by default and performs no network I/O. It ships via
 tag-triggered CI with npm provenance (OIDC Trusted Publishing); the GitHub
 Release re-registers the Official MCP Registry entry.
 
-**Status:** actively maintained · current public release **v0.40.3** · runs on Linux · WSL2 · macOS · native Windows (tmux on POSIX, the tmux-CLI-compatible [psmux](https://github.com/psmux/psmux) on native Windows — no WSL required) · MIT · see the [CHANGELOG](CHANGELOG.md).
+**Status:** actively maintained · current public release **v0.41.0** · runs on Linux · WSL2 · macOS · native Windows (tmux on POSIX, the tmux-CLI-compatible [psmux](https://github.com/psmux/psmux) on native Windows — no WSL required) · MIT · see the [CHANGELOG](CHANGELOG.md).
 
 ### Update and rollback
 
@@ -394,7 +394,7 @@ The only edits to the captures above are the two `⋮` lines (a long head/tail r
 `aiterm-setup --json`が`ready`になったら、利用するMCP clientを再起動して接続を確認する。Claude Codeの場合:
 
 ```bash
-/mcp        # aiterm should show as connected, exposing 17 tools
+/mcp        # aiterm should show as connected, exposing 16 tools
 ```
 
 Your first session — four calls, one persistent terminal:
@@ -435,7 +435,7 @@ The terminal is real and shared, so a human *can* jump in ([A human can watch](#
 
 ```mermaid
 flowchart LR
-    AI["AI / MCP client<br/>(the orchestrator)"] -->|"pty_send · pty_observe · agent_launch · agent_configure · agent_approval · claude_turn · claude_approval<br/>legacy launcher aliases · diagnostics"| S["aiterm-mcp<br/>stdio MCP · 17 tools"]
+    AI["AI / MCP client<br/>(the orchestrator)"] -->|"pty_send · pty_observe · agent_launch · agent_configure · agent_approval · claude_turn · claude_approval<br/>legacy launcher aliases · diagnostics"| S["aiterm-mcp<br/>stdio MCP · 16 tools"]
     S -->|"pty_read<br/>token-reduced"| AI
     S -->|"tmux / psmux<br/>send · capture"| P["persistent PTYs<br/>survive restarts"]
     P -->|"ssh · docker · repl"| R["nested<br/>remote · container · REPL"]
@@ -556,7 +556,7 @@ continue to use `claude_approval`.
 | `pty_observe` | Pane/harness liveness, native process identity, state, and activity | `session_id`, `cursor?` |
 | `agent_launch` | Canonical agent launch; harness and model are independent | `harness`, `prompt?`, `model?`, `reasoning_effort?`, `cwd?`, `write_scope?`, `trust_project?`, `env_vars?`, `throughline_source_session?`, `throughline_supplement_file?` |
 | `agent_approval` | Inspect a Codex approval and submit a one-time approval or denial | `action`, `session_id`, `approval_choice?`, `observed_prompt_digest?` |
-| `claude_agent` / `codex_agent` / `grok_agent` / `composer_agent` | Deprecated compatibility aliases (`composer_agent` is the old Grok CLI preset and cannot start now; run Composer with `agent_launch` on `cursor-cli`) | legacy launcher arguments |
+| `claude_agent` / `codex_agent` / `grok_agent` | Deprecated compatibility aliases (`composer_agent` was removed in 0.41.0; run Composer with `agent_launch` on `cursor-cli`) | legacy launcher arguments |
 | `agent_configure` | Change model/effort in a running Claude, Codex, Grok, or Cursor session without restarting it | `session_id`, `model?`, `reasoning_effort?` |
 | `claude_turn` | Issue (dispatch-only) or recover one correlated Claude operation | `action`, `session_id`, `operation_id`, `text?` |
 | `claude_approval` | Inspect or answer the current correlated Claude approval prompt | `action`, `session_id`, `operation_id?`, `approval_choice?`, `observed_prompt_digest?` |

package/dist/agent-resolver.js

@@ -29,7 +29,7 @@ export function isWindowsNativeExecutable(candidate) {
 // Windows の bin 受入: native 実行ファイル（.exe/.cmd/.bat）に加え、pane shell
 // （Git Bash）が shebang で実行できる script も実在すれば受け入れる。旧 WSL 側
 // バイナリ検査への黙ったフォールバックは廃止（別 HOME・別 auth の subagent を
-// 作るため）。native 実行ファイルの強制が要る harness（grok/composer の実効
+// 作るため）。native 実行ファイルの強制が要る harness（grok の実効
 // sandbox 等）は openAgent 側の専用ゲートが明示エラーで担う。
 export function isUsableAgentExecutableFile(candidate) {
     if (!isWin)

package/dist/agent-shared.js

@@ -177,13 +177,11 @@ export function writeAgentMetadata(meta) {
 export function agentLabel(kind) {
     return kind === "claude"
         ? "Claude Code"
-        : kind === "composer"
-            ? "Grok Build(Composer)"
-            : kind === "grok"
-                ? "Grok Build(Grok)"
-                : kind === "cursor"
-                    ? "Cursor Agent CLI"
-                    : "Codex";
+        : kind === "grok"
+            ? "Grok Build(Grok)"
+            : kind === "cursor"
+                ? "Cursor Agent CLI"
+                : "Codex";
 }
 export function agentHarness(kind) {
     return kind === "claude"
@@ -223,7 +221,7 @@ export function writeScopeLaunchNote(kind, writeScope) {
         ? ""
         : kind === "cursor" && writeScope === "read-only"
             ? `\n能力宣言: write_scope=${JSON.stringify(writeScope)}。Cursor Agent CLIへ --mode ask を付与し、書込みを実効禁止。`
-            : (kind === "codex" || kind === "grok" || kind === "composer") && writeScope === "read-only"
+            : (kind === "codex" || kind === "grok") && writeScope === "read-only"
                 ? `\n能力宣言: write_scope=${JSON.stringify(writeScope)}。${agentLabel(kind)} CLIへ --sandbox read-only を付与し、書込みを実効禁止。` +
                     (kind === "codex" ? "" : "MCPツール許可は --always-approve で自動承認（sandbox内のため能力拡大なし）。")
                 : `\n能力宣言: write_scope=${JSON.stringify(writeScope)}。パス単位のsandbox allowlistに対応するCLI引数がないため宣言の記録のみ（構造的unsupported）。`;

package/dist/core.js

@@ -18,7 +18,7 @@ import { readRuntimeProcesses, processSubtree, parentProcess, processIdentity, b
 import { AitermError, telemetryOwnedFailure, ownTelemetryFailure } from "./errors.js";
 import { isWin, SOCKDIR, tmuxCommand, sendPsmuxPayload, loadPtyBufferChunk, pasteBufferBaseArgs, TMUX_EMPTY_CONFIG, attachCommand, normalizePaneCommand, atomicShellMultiline, appendMarkSentinel, markShellCommand, settlePaneLog, paneCwdArgument, sessionEnvironmentLaunch, } from "./tmux-runtime.js";
 import { sleep, currentUid, runtimeStateBase, safeStatSize, readFileRange, writeJson0600, createEmpty0600, shq, LAUNCH_ID_RE, AGENT_DONE_POLL_MS, AGENT_EVENT_MAX_BYTES, assertSessionName, agentsDir, agentEventPath, agentMetadataPath, writeAgentMetadata, AGENT_EVENT_TAIL_BYTES, agentLabel, agentHarness, subagentInstruction, agentLineageFields, } from "./agent-shared.js";
-import { GROK_MODEL_DEFAULTS, realGrokHome, resolveAndValidateGrokAuth, assertGrokModelAvailable, grokEventsTranscript, latestGrokCompletion, observeGrokDone, buildGrokAgentCmd, grokLaunchNote, grokEnvTokens, grokTuiReady, grokTuiBusy, grokPaneObservation, grokRateLimitDialog, grokStartupAction, grokLaunchBlockingDialog, assertGrokSandboxNotRejected, GROK_COMPOSER_MARKER_RE, grokFooterHasConfiguration, grokTranscriptText, createGrokAgentMetadata, } from "./harnesses/grok.js";
+import { realGrokHome, resolveAndValidateGrokAuth, assertGrokModelAvailable, grokEventsTranscript, latestGrokCompletion, observeGrokDone, buildGrokAgentCmd, grokLaunchNote, grokEnvTokens, grokTuiReady, grokTuiBusy, grokPaneObservation, grokRateLimitDialog, grokStartupAction, grokLaunchBlockingDialog, assertGrokSandboxNotRejected, GROK_COMPOSER_MARKER_RE, grokFooterHasConfiguration, grokTranscriptText, createGrokAgentMetadata, } from "./harnesses/grok.js";
 import { bindCodexTranscriptSession, latestCodexCompletion, observeCodexDone, buildCodexAgentCmd, codexLaunchNote, codexTuiReady, codexPaneObservation, codexRateLimitModelSwitchDialog, codexApprovalDialog, codexStartupAction, CODEX_COMPOSER_MARKER_RE, codexModelChoice, codexEffortChoice, codexMoreReasoningChoice, codexTranscriptText, createCodexAgentMetadata, } from "./harnesses/codex.js";
 import { OPERATION_ID_RE, CLAUDE_RESULT_MAX_BYTES, CLAUDE_EFFORTS, agentManagedClaudeSettingsPath, agentClaudeResultPath, agentClaudeOperationPath, agentClaudeApprovalReceiptPath, agentClaudeDispatchReceiptPath, validateOperationId, readClaudeResultText, assertClaudeAuthenticationReady, buildClaudeAgentCmd, claudeLaunchNote, claudeTuiReady, claudePaneObservation, claudeStartupAction, claudeLoginMethodMenu, CLAUDE_COMPOSER_MARKER_RE, createClaudeAgentMetadata, claudeSessionTranscriptPath, claudeApiErrorFromLine, } from "./harnesses/claude.js";
 import { bindCursorTranscriptSession, cursorTurnBoundary, latestCursorCompletion, observeCursorDone, cursorTranscriptText, assertCursorAuthenticationReady, assertCursorModelAvailable, buildCursorAgentCmd, cursorAgentArgv, cursorPwshLaunchLine, cursorPromptWithLineage, createCursorAgentMetadata, cursorLaunchNote, cursorEffortNavigation, cursorTuiReady, cursorPaneObservation, cursorPromptHooksRunning, cursorUsageLimit, CURSOR_SUBMIT_SEQUENCE, CURSOR_COMPOSER_CONTENT_MARKER_RE, validateCursorModelEffort, } from "./harnesses/cursor.js";
@@ -121,7 +121,6 @@ const AGENT_COMMAND_PATTERNS = {
     codex: /(^|[\s/])codex([\s]|$)/,
     claude: /(^|[\s/])claude([\s]|$)/,
     grok: /(^|[\s/])grok(-[^\s/]+)?([\s]|$)/,
-    composer: /(^|[\s/])(composer|grok(-[^\s/]+)?)([\s]|$)/,
     cursor: /(^|[\s/])(cursor-agent|agent)([\s]|$)/,
 };
 /**
@@ -1134,7 +1133,7 @@ export function observeSession(name, cursor) {
     const screen = captured.stdout;
     result.token_hint = meta ? paneTokenHint(screen) : null;
     if (meta && agent) {
-        const observation = meta.kind === "grok" || meta.kind === "composer" ? grokPaneObservation(screen)
+        const observation = meta.kind === "grok" ? grokPaneObservation(screen)
             : meta.kind === "codex" ? codexPaneObservation(screen)
                 : meta.kind === "claude" ? claudePaneObservation(screen) : cursorPaneObservation(screen);
         result.state = observation.state;
@@ -1933,7 +1932,7 @@ function loadAgentMetadata(name) {
         throw new AitermError(`agent metadata を読めません: ${e.message}`, 2);
     }
     const m = raw;
-    if ((m.kind !== "claude" && m.kind !== "codex" && m.kind !== "grok" && m.kind !== "composer" && m.kind !== "cursor") ||
+    if ((m.kind !== "claude" && m.kind !== "codex" && m.kind !== "grok" && m.kind !== "cursor") ||
         m.aiterm_session !== name ||
         typeof m.launch_id !== "string" ||
         !LAUNCH_ID_RE.test(m.launch_id)) {
@@ -2191,7 +2190,7 @@ function bindCompletedInitialPrompt(meta) {
         setInitialPromptState(meta, "done");
         return;
     }
-    if ((meta.kind === "grok" || meta.kind === "composer") && meta.completion_route === "grok_transcript") {
+    if (meta.kind === "grok" && meta.completion_route === "grok_transcript") {
         if (!latestGrokCompletion(meta, readTranscriptLines)) {
             throw new AitermError(`agent session '${meta.aiterm_session}' は起動時 prompt の完了待ちです。${agentWaitGuide(meta.aiterm_session)}`, 2);
         }
@@ -2231,7 +2230,7 @@ function latestAgentDoneEvent(meta, expectedOperationId = null) {
     if (meta.kind === "cursor" && meta.completion_route === "cursor_transcript") {
         return latestCursorCompletion(meta, readTranscriptLines);
     }
-    if ((meta.kind === "grok" || meta.kind === "composer") && meta.completion_route === "grok_transcript") {
+    if (meta.kind === "grok" && meta.completion_route === "grok_transcript") {
         return latestGrokCompletion(meta, readTranscriptLines);
     }
     const size = safeStatSize(meta.event_file);
@@ -2323,7 +2322,7 @@ function recoverAgentHarnessSession(meta) {
     writeAgentMetadata(meta);
 }
 function agentCompletionCursor(meta) {
-    if ((meta.kind === "grok" || meta.kind === "composer") && meta.completion_route === "grok_transcript") {
+    if (meta.kind === "grok" && meta.completion_route === "grok_transcript") {
         const transcript = grokEventsTranscript(meta);
         return transcript ? safeStatSize(transcript) : 0;
     }
@@ -2409,7 +2408,7 @@ export async function readAgentTranscriptResult(name, o = {}) {
         throw new AitermError(`agent session '${name}' はまだターンが完了していません。agent_done 完了後に再取得してください。${agentWaitGuide(name)}`, 2);
     }
     const done = latestAgentDoneEvent(meta, operationId);
-    if (o.completion && meta.kind !== "codex" && meta.kind !== "grok" && meta.kind !== "composer"
+    if (o.completion && meta.kind !== "codex" && meta.kind !== "grok"
         && (!done || done.turn_id !== o.completion.turn_id || done.operation_id !== o.completion.operation_id)) {
         throw new AitermError("回収対象の完了情報が置換されました。別の回答は配送しません", 2);
     }
@@ -2607,7 +2606,7 @@ export function agentWaitGuide(session) {
     const cmd = `aiterm-wait --session ${session ?? "<session_id>"} --cursor 0`;
     return `完了通知は ${agentWaitLaunchForm(cmd)} で受ける（親はここで待たない・polling 不要）。receipt の outcome=done を確認してから再取得する。`;
 }
-// harness別の利用上限観測。Grok/Composerは現在の質問カード、Cursorは現在の画面、他harnessは既存logを使う。
+// harness別の利用上限観測。Grokは現在の質問カード、Cursorは現在の画面、他harnessは既存logを使う。
 // 出典（2026-08-22）: grok は live 実バナーで検証、codex/claude はインストール済み実バイナリの
 // 埋込文字列から抽出（codex: "You've hit your usage limit for" / claude: "Usage limit reached ·
 // continuing automatically when it resets"。Claude Code はリセット時に自動継続する設計なので、
@@ -2619,7 +2618,7 @@ const AGENT_RATE_LIMIT_PATTERNS = {
 const AGENT_RATE_LIMIT_SCAN_BYTES = 16 * 1024;
 // pane log の末尾から上限バナーを探す。読めない・無い・対象 harness でないは全て null（誤検知より取りこぼし側へ倒す）。
 export function detectAgentRateLimit(kind, aitermSession) {
-    if (kind === "grok" || kind === "composer") {
+    if (kind === "grok") {
         return grokRateLimitDialog(captureScreen(aitermSession, 0))?.message ?? null;
     }
     if (kind === "cursor")
@@ -2671,7 +2670,7 @@ export async function observeAgentDone(name, o = {}) {
     if (meta.kind === "cursor" && meta.completion_route === "cursor_transcript") {
         return observeCursorDone(meta, timeout, o.cursor, detectAgentRateLimit, (session) => captureScreen(session, 0), o.signal);
     }
-    if ((meta.kind === "grok" || meta.kind === "composer") && meta.completion_route === "grok_transcript") {
+    if (meta.kind === "grok" && meta.completion_route === "grok_transcript") {
         return observeGrokDone(meta, timeout, o.cursor, detectAgentRateLimit, o.signal);
     }
     const metadataFile = agentMetadataPath(meta.aiterm_session, meta.launch_id);
@@ -2769,13 +2768,13 @@ function isAgentTuiReady(kind, screen) {
 // Codex/Claude は実行中に「(esc to interrupt)」、Cursor は「Working」＋
 // 「ctrl+c to stop」を表示する（いずれも実機採取）。startup 側の処理（MCP initialize 等）が
 // 走ったまま古い composer がscrollbackに残る画面は入力受付とみなさない。
-// Grok/Composer は実機で `Waiting for response` / `Responding…` / `[stop]` を表示する。
+// Grok は実機で `Waiting for response` / `Responding…` / `[stop]` を表示する。
 function isAgentTuiBusy(kind, screen) {
     if (kind === "cursor")
         return /ctrl\+c to stop/i.test(screen);
     if (kind === "codex" || kind === "claude")
         return /esc to interrupt/i.test(screen);
-    if (kind === "grok" || kind === "composer") {
+    if (kind === "grok") {
         return grokTuiBusy(screen);
     }
     return false;
@@ -2783,7 +2782,7 @@ function isAgentTuiBusy(kind, screen) {
 // ready gate 用: 入力欄マーカーがあっても busy 表示中は ready と数えない。
 // frontend 推定（inferAgentFrontend）は「agent TUI が前面か」を見るだけなので isAgentTuiReady のまま。
 function isAgentTuiIdleReady(kind, screen) {
-    const observation = kind === "grok" || kind === "composer" ? grokPaneObservation(screen)
+    const observation = kind === "grok" ? grokPaneObservation(screen)
         : kind === "codex" ? codexPaneObservation(screen)
             : kind === "claude" ? claudePaneObservation(screen) : cursorPaneObservation(screen);
     return observation.state === "idle";
@@ -2791,7 +2790,7 @@ function isAgentTuiIdleReady(kind, screen) {
 // 起動側が明示応答すべき既知UI。ここで自動承認せず、ready timeoutを待たずに
 // `initial_prompt=not_sent`を返してsessionを生かしたままcallerへ制御を戻す。
 function isAgentTuiActionRequired(kind, screen) {
-    if (kind === "grok" || kind === "composer")
+    if (kind === "grok")
         return grokLaunchBlockingDialog(screen) !== null;
     if (kind === "codex") {
         return codexPaneObservation(screen).state === "blocked";
@@ -2830,7 +2829,7 @@ async function waitAgentTuiReadyImpl(kind, sample, sleepFn, opts = {}) {
     for (;;) {
         lastScreen = sample();
         samples++;
-        if (kind === "grok" || kind === "composer")
+        if (kind === "grok")
             assertGrokSandboxNotRejected(lastScreen);
         if (isAgentTuiIdleReady(kind, lastScreen)) {
             readyStreak++;
@@ -2873,7 +2872,7 @@ function agentSubmitResidueOnScreen(kind, screen, tail) {
     const lines = screen.split("\n");
     // 入力欄マーカーは ready 判定と同じ記号を行頭基準で探す。submit 済みの transcript echo は
     // マーカー行より上に出るため、最後のマーカー行以降だけを composer 領域として見る。
-    // grok/composer は Windows native 描画（`>`・実測 1.0.4）も ready 判定と同様に受ける。
+    // grok は Windows native 描画（`>`・実測 1.0.4）も ready 判定と同様に受ける。
     const markerRe = kind === "codex"
         ? CODEX_COMPOSER_MARKER_RE
         : kind === "claude"
@@ -3118,7 +3117,7 @@ async function prepareAgentInput(name, meta, options) {
     while (!ready.ready) {
         const action = meta.kind === "codex" ? codexStartupAction(ready.lastScreen, options.trust_project === true)
             : meta.kind === "claude" ? claudeStartupAction(ready.lastScreen, options.trust_project === true)
-                : meta.kind === "grok" || meta.kind === "composer" ? grokStartupAction(ready.lastScreen, options.trust_project === true) : null;
+                : meta.kind === "grok" ? grokStartupAction(ready.lastScreen, options.trust_project === true) : null;
         if (!action || handled.has(action.kind))
             break;
         handled.add(action.kind);
@@ -3145,7 +3144,7 @@ async function prepareAgentInput(name, meta, options) {
         ready = await waitAgentTuiReady(name, meta, options.ready_timeout ?? AGENT_TUI_READY_TIMEOUT_MS);
     }
     if (!ready.ready) {
-        const state = meta.kind === "grok" || meta.kind === "composer" ? grokPaneObservation(ready.lastScreen)
+        const state = meta.kind === "grok" ? grokPaneObservation(ready.lastScreen)
             : meta.kind === "codex" ? codexPaneObservation(ready.lastScreen)
                 : meta.kind === "claude" ? claudePaneObservation(ready.lastScreen) : cursorPaneObservation(ready.lastScreen);
         return { status: "blocked", reason: state.reason };
@@ -3217,7 +3216,7 @@ export async function sendInitialAgentPrompt(name, text, o = {}) {
     let screen = "";
     do {
         screen = captureScreen(name, AGENT_TUI_READY_LINES);
-        const state = meta.kind === "grok" || meta.kind === "composer" ? grokPaneObservation(screen)
+        const state = meta.kind === "grok" ? grokPaneObservation(screen)
             : meta.kind === "codex" ? codexPaneObservation(screen)
                 : meta.kind === "claude" ? claudePaneObservation(screen) : cursorPaneObservation(screen);
         if (state.state === "busy") {
@@ -3415,7 +3414,7 @@ export async function configureAgent(name, opts) {
             reasoning_effort: effort,
         };
     }
-    if (meta.kind === "grok" || meta.kind === "composer") {
+    if (meta.kind === "grok") {
         if (model) {
             const bin = resolveAgentBin(meta.kind);
             if (!bin)
@@ -3551,8 +3550,8 @@ export async function dispatchAgentTurn(name, text, o = {}) {
         throw new AitermError("operation_id はClaude agent sessionだけで使用できます", 2);
     }
     bindCompletedInitialPrompt(meta);
-    // Codex/Grok/Composerはbind済みのfollow-upでも毎回idleを確認してからtranscript境界を切る。
-    // Grok/Composerはsession IDが起動前から既知でも、共有MCPの初期化完了前には送信しない。
+    // Codex/Grokはbind済みのfollow-upでも毎回idleを確認してからtranscript境界を切る。
+    // Grokはsession IDが起動前から既知でも、共有MCPの初期化完了前には送信しない。
     // 同じcursorへ複数turnを帰属させる余地や、初期化中TUIへの早送信を作らない。
     // Claudeはsession IDを起動時に採番するため「bind済み」では初回を区別できず、起動直後の
     // dispatchがready gateを素通りしていた。composer描画前に貼付とEnterが届くと起動時の一塊の
@@ -3563,7 +3562,7 @@ export async function dispatchAgentTurn(name, text, o = {}) {
         && readClaudeOperationMarker(meta) === null;
     const paneInputRecovery = o.pane_input_recovery ?? await ensureAgentOwnsPaneInput(name, meta.kind);
     let codexRateLimitModelSwitch = false;
-    const limitDialog = meta.kind === "grok" || meta.kind === "composer"
+    const limitDialog = meta.kind === "grok"
         ? grokRateLimitDialog(captureScreen(name, 0)) : null;
     if (limitDialog) {
         const live = observeSession(name);
@@ -3736,7 +3735,7 @@ async function steerRunningTurn(name, meta, text, o) {
     sendKey(name, "Enter", { preserveAgentOperation });
     // GrokとCursorは実行中の送信を待ち行列へ入れる。そのままだと現在turnの完了後に別turnとして動き、
     // 完了通知が差し込み前の回答で届いてしまう。待ち行列へ入ったことを確かめ、標準の「今すぐ送る」で現在turnへ移す。
-    const queued = meta.kind === "grok" || meta.kind === "composer" ? grokSteerQueued
+    const queued = meta.kind === "grok" ? grokSteerQueued
         : meta.kind === "cursor" ? cursorSteerQueued : null;
     if (queued) {
         const label = meta.kind === "cursor" ? "Cursor" : "Grok";
@@ -3820,7 +3819,7 @@ function inspectClaudeOperation(meta, operationId, action) {
     const rawOutput = readClaudeResultText(meta, done, operationId, transcriptUnavailable);
     return { ...base, status: "completed", raw_output: rawOutput, reason: null };
 }
-// ── 対話型エージェント起動（Claude / Codex / Grok Build(Grok) / Grok Build(Composer)）──────
+// ── 対話型エージェント起動（Claude / Codex / Grok Build / Cursor）──────
 // aiterm の永続端末に、指定モデルの対話エージェント TUI を起動する。以後は pty_read で画面を
 // 読み、pty_send で操作する＝aiterm の対話パラダイムそのもの。モデルはツールごとに固定し、
 // reasoning effort は引数で渡す。CLI 未導入環境は明示エラー（動くフリをしない）。
@@ -4063,21 +4062,20 @@ export function openAgent(kind, opts = {}) {
     // 未検証リスク: npm グローバル導入の codex.cmd/.bat シムの対話 TUI 描画は実 Windows でしか確認
     // できない（CI 非対象。docs/03_audit-sweep-2026-07.md 参照）。native .exe の TUI 描画は
     // grok.exe で実測済み（2026-08-15）。
-    // Windows の grok/composer は Windows native の grok.exe だけを起動する（オーナー裁定 2026-08-15:
+    // Windows の grok は Windows native の grok.exe だけを起動する（オーナー裁定 2026-08-15:
     // WindowsネイティブはWindowsネイティブで完結させ、WSL2へ持ち込まない）。WSL 側 grok を起動すると
     // harness 実体が WSL process になり、auth・session 記録（events/chat_history）が WSL home 側へ分裂して
     // transcript／completion を回収できない（実被弾: 2026-08-15 olc-plan-review-grok2）。
-    if (isWin && (kind === "grok" || kind === "composer") && !isWindowsNativeExecutable(bin)) {
+    if (isWin && kind === "grok" && !isWindowsNativeExecutable(bin)) {
         ownTelemetryFailure("AITERM.VENDOR_LAUNCHER_FAILED", new AitermError(`Windows の ${label} launcher は Windows native の grok.exe だけを起動できます（現在の解決先: ${bin}）。` +
             "Windows 版 Grok CLI を導入するか、GROK_BIN に grok.exe の絶対パスを指定してください。", 2), 2);
     }
     const binForCmd = agentBinForPaneShell(bin);
     const cwdForCmd = cwd ? paneCwdArgument(cwd) : cwd;
-    const grokAuthPath = agentDone && (kind === "grok" || kind === "composer") ? resolveAndValidateGrokAuth(realGrokHome()) : null;
-    if (kind === "grok" || kind === "composer") {
-        const requestedModel = model ?? (kind === "composer" ? GROK_MODEL_DEFAULTS.composer : null);
-        if (requestedModel)
-            assertGrokModelAvailable(bin, cwd ?? process.cwd(), requestedModel);
+    const grokAuthPath = agentDone && kind === "grok" ? resolveAndValidateGrokAuth(realGrokHome()) : null;
+    if (kind === "grok") {
+        if (model)
+            assertGrokModelAvailable(bin, cwd ?? process.cwd(), model);
     }
     if (kind === "cursor" && model) {
         assertCursorModelAvailable(bin, cwd ?? process.cwd(), model, effort);

package/dist/cursor-parent-receiver.js

@@ -11,7 +11,7 @@ export const cursorParentSchema = z.object({
 }).strict();
 const deliveryIdSchema = z.string().uuid();
 const dispatchTools = new Set([
-    "agent_launch", "claude_agent", "codex_agent", "grok_agent", "composer_agent", "pty_send", "claude_turn",
+    "agent_launch", "claude_agent", "codex_agent", "grok_agent", "pty_send", "claude_turn",
 ]);
 export class CursorDeliveryError extends AitermError {
     delivery_code;

package/dist/grok-stop-hook.js

@@ -64,8 +64,8 @@ async function main() {
     const kind = process.env.AITERM_AGENT_KIND;
     const session = process.env.AITERM_SESSION_ID || process.env.AITERM_AGENT_SESSION_ID || "";
     const launchId = process.env.AITERM_AGENT_LAUNCH_ID || "";
-    if (kind !== "grok" && kind !== "composer")
-        fail(`AITERM_AGENT_KIND が grok/composer ではありません: ${kind ?? ""}`);
+    if (kind !== "grok")
+        fail(`AITERM_AGENT_KIND が grok ではありません: ${kind ?? ""}`);
     if (!SESSION_RE.test(session))
         fail(`session id が不正です: ${session}`);
     if (!LAUNCH_ID_RE.test(launchId))

package/dist/harnesses/grok.js

@@ -1,6 +1,5 @@
-// Grok 固有の制御。kind "composer" は旧互換alias composer_agent 用の旧Grok CLI presetで、
-// モデル既定値と表示名以外は Grok と完全共通。Composer は現在 Cursor の model の一つであり、
-// 現行Grok CLIには無い（2026-09-27 grok 1.0.41 実測）。
+// Grok 固有の制御。Composer は Cursor の model の一つであり、Grok CLI では扱わない
+// （2026-09-27 grok 1.0.41 実測でcatalogに無い）。
 // core 所有のサービス（transcript 行読取・rate limit 検知）は引数で注入し、
 // 依存方向を core → harnesses → agent-shared の一方向に保つ。
 import * as fs from "node:fs";
@@ -17,7 +16,6 @@ const GROK_MODELS_TIMEOUT_MS = 15_000;
 // 製品既定は検証済みGrok catalog世代へ固定する。callerの明示modelはlive catalogで別途照合する。
 export const GROK_MODEL_DEFAULTS = {
     grok: "grok-4.6",
-    composer: "grok-composer-2.5-fast",
 };
 export function realGrokHome() {
     return path.resolve(process.env.GROK_HOME || path.join(process.env.HOME ?? os.homedir(), ".grok"));
@@ -71,7 +69,7 @@ export function assertGrokModelAvailable(bin, cwd, model) {
     }
 }
 export function grokSessionDirectory(meta) {
-    if ((meta.kind !== "grok" && meta.kind !== "composer") || !meta.grok_home || !meta.vendor_session_id)
+    if (meta.kind !== "grok" || !meta.grok_home || !meta.vendor_session_id)
         return null;
     // Grok CLIは起動cwdをOSの絶対パスへ正規化して保存する。
     const cwd = path.resolve(meta.cwd ?? process.cwd());
@@ -82,7 +80,7 @@ export function grokEventsTranscript(meta) {
     return dir ? path.join(dir, "events.jsonl") : null;
 }
 export function grokCompletionEvent(meta, record) {
-    if ((meta.kind !== "grok" && meta.kind !== "composer") ||
+    if (meta.kind !== "grok" ||
         record?.type !== "turn_ended" ||
         (record?.outcome !== "completed" && record?.outcome !== "cancelled" && record?.outcome !== "error"))
         return null;
@@ -240,24 +238,23 @@ export async function observeGrokDone(meta, timeout, requestedCursor, detectRate
 }
 export function buildGrokAgentCmd(kind, bin, model, effort, prompt, meta) {
     const parts = [shq(bin)];
-    // grok / composer は同じ grok CLI をモデル違いで起動する。
     parts.push("--no-auto-update");
     // 無人起動の対象cwdはCLIの公式folder trust指定で登録し、確認画面にpromptを消費させない。
-    if (meta?.kind === "grok" || meta?.kind === "composer")
+    if (meta?.kind === "grok")
         parts.push("--no-alt-screen", "--trust");
     parts.push("--model", shq(model ?? GROK_MODEL_DEFAULTS[kind]));
     if (effort)
         parts.push("--reasoning-effort", shq(effort));
-    if ((meta?.kind === "grok" || meta?.kind === "composer") && meta.write_scope === "read-only") {
+    if (meta?.kind === "grok" && meta.write_scope === "read-only") {
         // read-only は sandbox が実効書込み禁止を作るため、MCP ツール許可ダイアログの自動承認を
         // 付けても能力は増えない。無人 subagent が初回 MCP 使用の許可待ちで停止する実障害への対処。
         // read-only 以外の launch には付けない＝権限拡大しない。
         parts.push("--sandbox", "read-only", "--always-approve");
     }
-    if ((meta?.kind === "grok" || meta?.kind === "composer") && meta.hook_route === "shared_grok_home") {
+    if (meta?.kind === "grok" && meta.hook_route === "shared_grok_home") {
         parts.push("--session-id", shq(meta.vendor_session_id ?? ""), "--rules", shq(subagentInstruction(meta)));
     }
-    if ((meta?.kind === "grok" || meta?.kind === "composer") && prompt)
+    if (meta?.kind === "grok" && prompt)
         parts.push("--verbatim");
     if (prompt)
         parts.push(shq(prompt)); // 初手プロンプト（任意）
@@ -268,7 +265,7 @@ export function grokLaunchNote(kind, model, effort, meta) {
     return (`起動設定: model=${model ?? GROK_MODEL_DEFAULTS[kind]}（${model ? "引数" : "ツール既定"}）。` +
         `effort=${effort ?? "CLI／model既定"}。` + writeScopeNote);
 }
-// grok/composer: 検証済み auth 正本をそのままの path 形で渡す。Windows では native 強制により
+// grok: 検証済み auth 正本をそのままの path 形で渡す。Windows では native 強制により
 // harness は Windows process なので、Windows ドライブパスが正しい形（WSL 形への変換はしない）。
 export function grokEnvTokens(meta) {
     return [
@@ -304,9 +301,8 @@ export function grokTuiReady(screen) {
     if (grokLaunchBlockingDialog(screen))
         return false;
     // Grok Build 0.2.117 は起動完了後に製品名を消し、model footerだけを残す。
-    // Composerも同じfrontendでmodel名だけが異なるため、両方をharness UIの根拠にする。
     // Windows native grok.exe（1.0.4 実測）は入力欄markerを `❯` でなく `>` で描画するため両方を受ける。
-    const grokFrontend = screen.includes("Grok Build") || /\b(?:Grok|Composer)\s+[\w.()-]+/.test(screen);
+    const grokFrontend = screen.includes("Grok Build") || /\bGrok\s+[\w.()-]+/.test(screen);
     return grokFrontend && /(^|\n|\s)[❯>]/.test(screen);
 }
 export function grokTuiBusy(screen) {
@@ -334,7 +330,7 @@ export function grokRateLimitDialog(screen) {
     return { message: "You hit your weekly limit.", dismissKey: "X" };
 }
 function grokFramedComposer(screen) {
-    return /^[ \t]*│[ \t]*[❯>][^\n]*\n(?:[ \t]*│[^\n]*\n)*[ \t]*╰[^\n]*\b(?:Grok|Composer)\s+[\w.()-]+[^\n]*╯[ \t]*(?:\n|$)/mu.test(screen);
+    return /^[ \t]*│[ \t]*[❯>][^\n]*\n(?:[ \t]*│[^\n]*\n)*[ \t]*╰[^\n]*\bGrok\s+[\w.()-]+[^\n]*╯[ \t]*(?:\n|$)/mu.test(screen);
 }
 export function grokPaneObservation(screen) {
     // 通信失敗後もWaitingが残る実画面を、稼働中として返さない。

package/dist/index.js

@@ -122,7 +122,7 @@ async function factoryDiagnostics() {
             grok: {
                 status: grok,
                 optional: true,
-                required_for: ["grok_agent", "composer_agent"],
+                required_for: ["grok_agent"],
             },
             cursor: {
                 status: cursor,
@@ -292,7 +292,7 @@ registerRemoteAwareTool("pty_send", {
         wait_process: waitProcessOutputSchema,
         parent_delivery: parentDeliveryOutputSchema.optional(),
         launch_id: z.string().nullable(),
-        vendor: z.enum(["claude", "codex", "grok", "composer", "cursor"]).nullable(),
+        vendor: z.enum(["claude", "codex", "grok", "cursor"]).nullable(),
         harness: z.enum(["claude-code", "codex-cli", "grok-cli", "cursor-cli"]).nullable(),
         // dispatch後のsubmit座礁観測（additive）。true=composerに送信textの残存を確認（submit未成立の疑い）/
         // false=残存を観測せず（成立の保証ではない）/ null=通常送信・判定不能。
@@ -426,7 +426,7 @@ registerRemoteAwareTool("pty_read", {
         mode: z.enum(["terminal", "agent_transcript"]),
         session_id: z.string(),
         text: z.string(),
-        vendor: z.enum(["claude", "codex", "grok", "composer", "cursor"]).nullable(),
+        vendor: z.enum(["claude", "codex", "grok", "cursor"]).nullable(),
         turn_id: z.string().nullable(),
         harness: z.enum(["claude-code", "codex-cli", "grok-cli", "cursor-cli"]).nullable(),
         raw_chars: z.number().int().nonnegative().nullable(),
@@ -726,7 +726,7 @@ registerRemoteAwareTool("agent_configure", {
     outputSchema: {
         schema: z.literal("aiterm.agent-configure-result.v1"),
         session_id: z.string().regex(/^[A-Za-z0-9_-]{1,64}$/),
-        provider: z.enum(["claude", "codex", "grok", "composer", "cursor"]),
+        provider: z.enum(["claude", "codex", "grok", "cursor"]),
         harness: z.enum(["claude-code", "codex-cli", "grok-cli", "cursor-cli"]),
         model: z.string().nullable(),
         reasoning_effort: z.string().nullable(),
@@ -752,10 +752,7 @@ const agentModelDesc = (kind) => kind === "claude"
             "（端末側のピンがそのまま効く。実効値は起動応答に明示される）"
         : kind === "cursor"
             ? "Cursor Agent CLIで選ぶbase model（例: gpt-5.6-luna）。GPT／Claude／Grok等を選べ、effortは別指定。省略時はCursor既定"
-            : `起動モデル。省略時は ${kind === "grok" ? "grok-4.6" : "grok-composer-2.5-fast"}。` +
-                (kind === "composer"
-                    ? "既定／explicit modelを起動前にlive catalogへ照合し、不在ならfallbackせずエラー"
-                    : "explicit modelを起動前にlive catalogへ照合し、不在ならfallbackせずエラー");
+            : "起動モデル。省略時は grok-4.6。explicit modelを起動前にlive catalogへ照合し、不在ならfallbackせずエラー";
 const agentEffortDesc = (kind) => kind === "claude"
     ? "Claude Code reasoning effort。low/medium/high/xhigh/max。省略時はCLI既定"
     : kind === "codex"
@@ -965,7 +962,7 @@ server.registerTool("agent_launch", {
         remote_host: z.string().optional().describe("別端末で起動した時の接続先"),
         remote_version: z.string().nullable().optional().describe("別端末のAiterm版"),
         harness: z.enum(["claude-code", "codex-cli", "grok-cli", "cursor-cli"]),
-        provider: z.enum(["claude", "codex", "grok", "composer", "cursor"]).describe("旧互換field。新規連携はharnessを使う"),
+        provider: z.enum(["claude", "codex", "grok", "cursor"]).describe("旧互換field。新規連携はharnessを使う"),
         session_id: z.string().regex(/^[A-Za-z0-9_-]{1,64}$/),
         managed_completion: z.boolean(),
         event_cursor: z.number().int().nullable(),
@@ -1006,12 +1003,6 @@ registerAgentTool("grok_agent", "grok", "【旧互換alias。新規連携は age
     "turn は pty_send で送る（自動で非ブロック dispatch になる）。" +
     agentCompletionDesc +
     "model／reasoning_effortを引数で指定可。read-only sandboxとagent_configureに対応。");
-registerAgentTool("composer_agent", "composer", "【旧互換alias・起動不能。ComposerはCursorのmodelの一つなので agent_launch(harness=cursor-cli, model=composer-2.5-fast) を使う】旧Grok CLIのComposer presetを起動しようとする。現行Grok CLIにComposerは無く、常にcatalogエラーになる。" +
-    agentEnvironmentDesc +
-    "turn は pty_send で送る（自動で非ブロック dispatch になる）。" +
-    agentCompletionDesc +
-    "model／reasoning_effortを引数で指定可。live catalogにComposer modelがなければGrokへfallbackせず明示エラー。" +
-    "read-only sandboxとagent_configureに対応。");
 async function main() {
     // 親ホストを initialize の clientInfo.name から確定させ、receipt の完了待ちコマンドを
     // そのホストの実際の起動形で名指しする（実測: claude-code は initialize → notifications/initialized

package/dist/parent-delivery.js

@@ -21,7 +21,7 @@ const recordSchema = z.object({
     boundary: z.object({
         session_id: z.string().regex(/^[A-Za-z0-9_-]{1,64}$/),
         launch_id: z.string().regex(/^[0-9a-f]{32}$/),
-        vendor: z.enum(["claude", "codex", "grok", "composer", "cursor"]),
+        vendor: z.enum(["claude", "codex", "grok", "cursor"]),
         harness: z.enum(["claude-code", "codex-cli", "grok-cli", "cursor-cli"]),
         event_cursor: z.number().int().nonnegative(), operation_id: z.string().nullable(),
         // 別端末の子。remote用の保存場所にだけ書き、旧版のreaderへ渡さない。

package/dist/setup-integrations.js

@@ -58,7 +58,7 @@ export function mergeJsonMcp(file, registration) {
 }
 export function claudeParentHookEntries(registration) {
     const command = { type: "command", command: registration.command, args: [join(dirname(registration.args[0]), "claude-parent-hook.js")] };
-    const matcher = "^mcp__aiterm__(agent_launch|claude_agent|codex_agent|grok_agent|composer_agent|pty_send|claude_turn)$";
+    const matcher = "^mcp__aiterm__(agent_launch|claude_agent|codex_agent|grok_agent|pty_send|claude_turn)$";
     return {
         PreToolUse: [{ matcher, hooks: [{ ...command, timeout: 15 }] }],
         PostToolUse: [{ matcher, hooks: [{ ...command, asyncRewake: true, timeout: 86400 }] }],

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "aiterm-mcp",
-  "version": "0.40.3",
+  "version": "0.41.0",
   "mcpName": "io.github.kitepon/aiterm-mcp",
   "description": "Persistent terminal MCP with one harness-based launcher for Claude Code, Codex CLI, Grok CLI, and Cursor Agent CLI, plus durable PTYs for SSH, containers, and REPLs.",
   "keywords": [