codemini-cli 0.3.7 → 0.3.8

package/OPERATIONS.md

@@ -120,6 +120,9 @@ Use this when you want to separate:
 /spec <topic>
 /plan <goal>
 /plan auto <goal>
+/yes
+/edit <feedback>
+/reject
 /plan from-spec <path?>
 /agents list
 /agents run <role> <task>
@@ -130,6 +133,7 @@ Use this when you want to separate:
 Note:
 - The old manual `/tasks` board has been removed.
 - For complex single-task work, the assistant now maintains an internal session todo checklist automatically and shows it in the TUI.
+- `/plan auto run` is deprecated. Use `/plan auto <goal>` then `/yes`, `/edit <feedback>`, or `/reject`.
 
 Available sub-agent roles:
 
@@ -171,6 +175,20 @@ Then continue with:
 Execute this plan step by step.
 ```
 
+For auto plan approval flow:
+
+```text
+/plan auto <goal>
+/yes
+```
+
+or revise/discard before execution:
+
+```text
+/edit <feedback>
+/reject
+```
+
 ### Session recovery
 
 ```text

package/README.md

@@ -1,14 +1,23 @@
-# CodeMini CLI
+# [CodeMini CLI](https://github.com/havingautism/Codemini-CLI)
 
+[![npm version](https://img.shields.io/npm/v/codemini-cli.svg?style=flat-square)](https://www.npmjs.com/package/codemini-cli)
+[![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg?style=flat-square)](LICENSE)
+[![Node.js >= 22](https://img.shields.io/badge/Node.js-%3E%3D%2022-339933.svg?style=flat-square&logo=node.js)](https://nodejs.org)
 [![English](https://img.shields.io/badge/README-English-0f172a?style=for-the-badge)](#english)
 [![简体中文](https://img.shields.io/badge/README-%E7%AE%80%E4%BD%93%E4%B8%AD%E6%96%87-2563eb?style=for-the-badge)](#简体中文)
 
+---
+
+<a id="english"></a>
+
 ## English
 
 CodeMini CLI is a terminal coding assistant built for teams that want a sharper, more controllable, and model-agnostic agent experience.
 
 It is designed around a deliberate idea: most coding workflows do not need a huge default tool surface or unrestricted shell behavior. Instead, CodeMini starts with a compact core, loads advanced tools on demand, and keeps the agent grounded in structured code operations, session todos, lightweight project indexing, and shell-aware safety rules.
 
+**Contents** — [Why CodeMini CLI](#why-codemini-cli) · [Installation](#installation) · [Quick Start](#quick-start) · [Commands](#commands) · [Personalities (Souls)](#personalities-souls) · [Tool Model](#how-the-tool-model-works) · [Core Capabilities](#core-capabilities) · [Project Index](#project-index) · [Good Fit](#good-fit) · [Documentation](#documentation) · [Development](#development) · [License](#license)
+
 ### Why CodeMini CLI
 
 - Built for practical coding workflows across both frontier-scale and smaller/internal models
@@ -17,89 +26,65 @@ It is designed around a deliberate idea: most coding workflows do not need a hug
 - Prefers structured file and code tools over noisy shell fallbacks
 - Supports planning, execution, todo tracking, and sub-agent workflows without forcing a bloated interface
 
-### What It Feels Like
+### Installation
 
-- A coding CLI that is fast to steer
-- A tool surface that is easier to audit and reason about
-- A TUI that makes execution visible instead of hiding agent state
-- A workflow that stays reliable across both large and small models
+Requires **Node.js ≥ 22**.
 
-### Core Capabilities
+```bash
+# Install globally
+npm install -g codemini-cli
 
-- Compact default tools for daily work:
-  - `read`
-  - `grep`
-  - `list`
-  - `query_project_index`
-  - `edit`
-  - `write`
-  - `update_todos`
-  - `run`
-  - `tool_search`
-- On-demand tools for advanced workflows:
-  - `glob`
-  - AST tools: `ast_query`, `read_ast_node`
-  - diff tools: `generate_diff`, `patch`
-  - background task management tools
-  - persistent memory tools
-- Session-scoped todo tracking through `update_todos`, rendered directly in the TUI
-- Unified shell execution model:
-  - one-shot commands through `run`
-  - long-running commands through `run` with `run_in_background=true`
-  - background task inspection through deferred tools when needed
-- Lightweight project index in `.codemini-project/` for repository-aware prompting
-- Tree-sitter-assisted structural editing for function/class/method scoped work
-- Sub-agent support for planning, coding, review, and testing workflows
-- Reply language control through `ui.reply_language`
-- Tone presets through `soul`, without changing planning or code behavior
-
-### Workflow Highlights
-
-- `update_todos` is used for complex single-task work and rendered as a native checklist in the TUI
-- `plan auto` is oriented toward task decomposition and execution sequencing
-- `task`-level execution tracking is separated from `plan` and handled through the internal todo checklist
-- The shell workflow is unified: the assistant no longer has to switch mental models between one-shot commands and long-running service tools
-- The prompt explicitly teaches the model that the visible default tools are not the full tool universe; it should use `tool_search` when it needs more capability
-- Slash completion includes prioritization, paging, and inline descriptions
-- Safe mode is enabled by default
+# Or run without installing
+npx codemini-cli
+```
 
 ### Quick Start
 
 ```bash
+# 1. Configure your gateway and model
 codemini config set gateway.base_url http://your-internal-gateway/v1
 codemini config set gateway.api_key your_token
 codemini config set model.name your-preferred-model
-codemini config set shell.default powershell
+
+# 2. Set shell (PowerShell for Windows, bash for macOS/Linux)
+codemini config set shell.default powershell   # Windows
+codemini config set shell.default bash         # macOS / Linux
+
+# 3. Optional: set reply language and run diagnostics
 codemini config set ui.reply_language zh
 codemini doctor
+
+# 4. Start an interactive coding session
 codemini
 ```
 
-For macOS or Linux:
+### Commands
 
-```bash
-codemini config set shell.default bash
-```
+| Command | Description |
+|---------|-------------|
+| `codemini [prompt]` | Start an interactive coding session with an optional initial prompt |
+| `codemini chat [prompt]` | Chat mode — single-turn or multi-turn conversation |
+| `codemini run <task>` | Run a task non-interactively (e.g. `codemini run "fix the login bug"`) |
+| `codemini config set\|get\|list <key> [value]` | Manage configuration (gateway, model, shell, UI, soul, etc.) |
+| `codemini doctor` | Run environment diagnostics and validate configuration |
+| `codemini skill list\|install\|enable\|disable\|inspect\|reindex` | Manage skills — list, install, toggle, or inspect bundled/third-party skills |
 
-### Commands
+### Personalities (Souls)
 
-```text
-codemini [prompt]
-codemini chat [prompt]
-codemini run <task>
-codemini config set|get|list <key> [value]
-codemini doctor
-codemini skill list|install|enable|disable|inspect|reindex
+CodeMini CLI supports swappable "soul" personalities that change tone and expression style without altering plan logic or code behavior.
+
+Built-in souls: `default`, `professional`, `ceo`, `playful`, `anime`, `caveman`, `pirate`
+
+```bash
+codemini config set soul.preset playful
 ```
 
 ### How The Tool Model Works
 
 CodeMini CLI intentionally separates tools into two layers:
 
-- Default tools:
-  always visible, optimized for the most common coding path
-- Deferred tools:
-  loaded only when needed through `tool_search`
+- **Default tools** — always visible, optimized for the most common coding path
+- **Deferred tools** — loaded only when needed through `tool_search`
 
 This keeps the main interface smaller and makes the agent's first-choice behavior more predictable.
 
@@ -112,18 +97,37 @@ Typical flow:
 5. `update_todos` to keep complex work legible
 6. `tool_search` only when a more specialized capability is needed
 
+### Core Capabilities
+
+- Compact default tools for daily work:
+  - `read`, `grep`, `glob`, `list`, `query_project_index`
+  - `edit`, `write`
+  - `read_plan`, `update_plan`, `update_todos`
+  - `run`, `tool_search`
+- On-demand tools for advanced workflows:
+  - AST tools: `ast_query`, `read_ast_node`
+  - background task management tools
+  - persistent memory tools
+- Session-level todo checklists via `update_todos`, rendered natively in the TUI
+- Unified shell execution model:
+  - one-off commands via `run`
+  - long-running commands via `run` with `run_in_background=true`
+- Lightweight project index under `.codemini-project/`
+- Tree-sitter based structured editing for function, class, and method-level changes
+- Reply language control via `ui.reply_language`
+- Safe mode enabled by default
+
 ### Project Index
 
 CodeMini CLI maintains a lightweight project index inside `.codemini-project/`:
 
-- `project-map.json`
-  high-level repository facts such as languages, source roots, test roots, and entry candidates
-- `file-index.json`
-  per-file structure such as imports, exports, functions, classes, and lightweight symbol hints
+- `project-map.json` — high-level repository facts such as languages, source roots, test roots, and entry candidates
+- `file-index.json` — per-file structure such as imports, exports, functions, classes, and lightweight symbol hints
 
 The index is initialized when entering a project and refreshed incrementally after edits, writes, and patches. It is intended to be factual, compact, and inexpensive to keep current.
 
-### Data Layout
+<details>
+<summary>Data Layout &amp; Config Paths</summary>
 
 - Global session state: `<base-config-dir>/sessions/`
 - Project workspace state: `.codemini/`
@@ -134,17 +138,15 @@ The index is initialized when entering a project and refreshed incrementally aft
 
 Base config directory resolution order:
 
-- `CODEMINI_GLOBAL_DIR`
-- Windows: `%APPDATA%\codemini-global\`
-- macOS: `~/Library/Preferences/codemini-global`
-- Linux / XDG: `$XDG_CONFIG_HOME/codemini-global`
-- Restricted fallback: `.codemini-global/`
+| Platform | Path |
+|----------|------|
+| `CODEMINI_GLOBAL_DIR` env | `$CODEMINI_GLOBAL_DIR` (highest priority) |
+| Windows | `%APPDATA%\codemini-global\` |
+| macOS | `~/Library/Preferences/codemini-global` |
+| Linux / XDG | `$XDG_CONFIG_HOME/codemini-global` |
+| Restricted fallback | `.codemini-global/` |
 
-### Documentation
-
-- Operator guide and workflow notes: [OPERATIONS.md](./OPERATIONS.md)
-- Packaging and deployment: [deployment.md](./deployment.md)
-- Release process: [RELEASE_CHECKLIST.md](./RELEASE_CHECKLIST.md)
+</details>
 
 ### Good Fit
 
@@ -156,11 +158,36 @@ CodeMini CLI is a strong fit if you want:
 - a TUI that shows plans, todos, tools, and progress clearly
 - a code assistant that prefers structured operations over shell noise
 
+### Documentation
+
+- Operator guide and workflow notes: [OPERATIONS.md](./OPERATIONS.md)
+- Packaging and deployment: [deployment.md](./deployment.md)
+- Changelog: [Releases](https://github.com/havingautism/Codemini-CLI/releases)
+
+### Development
+
+```bash
+# Install dependencies
+npm install
+
+# Run tests
+npm test
+
+# Start locally
+npm start
+```
+
+### License
+
+[MIT](LICENSE)
+
 ---
 
+<a id="简体中文"></a>
+
 ## 简体中文
 
-CodeMini CLI 是一个面向真实开发环境的终端代码助手，目标不是“把所有能力都塞进默认界面”，而是做一个更克制、更清晰、更容易掌控的 coding agent CLI。
+CodeMini CLI 是一个面向真实开发环境的终端代码助手，目标不是"把所有能力都塞进默认界面"，而是做一个更克制、更清晰、更容易掌控的 coding agent CLI。
 
 它围绕一个很明确的原则来设计：默认工具面尽量小，常用路径尽量顺，复杂能力按需加载。这样可以同时兼顾大模型与小模型，也适合团队在内部环境里做稳定、可控的日常开发协作。
 
@@ -172,93 +199,69 @@ CodeMini CLI 是一个面向真实开发环境的终端代码助手，目标不
 - 优先走结构化代码工具，而不是让模型长期泡在嘈杂 shell 输出里
 - 同时支持规划、执行、待办追踪和 sub-agent 协作，但不把界面做得臃肿
 
-### 使用体验
-
-- 更容易 steer 的 coding CLI
-- 更容易审计和理解的工具面
-- 更强调执行可视化的 TUI
-- 即使模型不是 frontier 级别，也依然能稳定工作
+### 安装
 
-### 核心能力
+需要 **Node.js ≥ 22**。
 
-- 默认主工具保持在高频主路径：
-  - `read`
-  - `grep`
-  - `list`
-  - `query_project_index`
-  - `edit`
-  - `write`
-  - `update_todos`
-  - `run`
-  - `tool_search`
-- 更专业的能力按需加载：
-  - `glob`
-  - AST 工具：`ast_query`、`read_ast_node`
-  - diff 工具：`generate_diff`、`patch`
-  - 后台任务管理工具
-  - 持久 memory 工具
-- 通过 `update_todos` 维护复杂单任务的会话级待办清单，并直接渲染在 TUI 中
-- 统一的 shell 执行模型：
-  - 一次性命令直接 `run`
-  - 长运行命令通过 `run` + `run_in_background=true`
-  - 需要时再加载后台任务管理工具
-- 在 `.codemini-project/` 下维护轻量项目索引，帮助模型更快理解仓库
-- 基于 Tree-sitter 的结构化编辑能力，适合函数级、类级、方法级改动
-- 支持 planner、coder、reviewer、tester 等 sub-agent 协作
-- 支持通过 `ui.reply_language` 控制回复语言
-- `soul` 只影响语气和表达，不改变计划或代码行为
-
-### 工作流亮点
+```bash
+# 全局安装
+npm install -g codemini-cli
 
-- 复杂单任务会使用 `update_todos`，并在 TUI 里以原生 checklist 方式展示
-- `plan auto` 专注于任务拆解、顺序和执行编排
-- 单任务内部的执行推进则由 todo checklist 负责，不和 `plan` 混在一起
-- shell 模型已经统一，不再需要在“一次性命令”和“长运行服务工具”之间切换心智
-- prompt 会明确告诉模型：默认看到的工具不是全部工具，缺能力时先 `tool_search`
-- slash 补全支持优先级、分页和简短说明
-- safe mode 默认开启
+# 或不安装直接运行
+npx codemini-cli
+```
 
 ### 快速开始
 
 ```bash
+# 1. 配置网关和模型
 codemini config set gateway.base_url http://your-internal-gateway/v1
 codemini config set gateway.api_key your_token
 codemini config set model.name your-preferred-model
-codemini config set shell.default powershell
+
+# 2. 设置 shell（Windows 用 PowerShell，macOS/Linux 用 bash）
+codemini config set shell.default powershell   # Windows
+codemini config set shell.default bash         # macOS / Linux
+
+# 3. 可选：设置回复语言，运行诊断
 codemini config set ui.reply_language zh
 codemini doctor
+
+# 4. 启动交互式编码会话
 codemini
 ```
 
-如果你在 macOS 或 Linux：
+### 命令概览
 
-```bash
-codemini config set shell.default bash
-```
+| 命令 | 说明 |
+|------|------|
+| `codemini [prompt]` | 启动交互式编码会话，可附带初始提示 |
+| `codemini chat [prompt]` | 对话模式——单轮或多轮 |
+| `codemini run <task>` | 非交互式执行任务（如 `codemini run "修复登录 bug"`） |
+| `codemini config set\|get\|list <key> [value]` | 管理配置（网关、模型、shell、UI、soul 等） |
+| `codemini doctor` | 运行环境诊断并验证配置 |
+| `codemini skill list\|install\|enable\|disable\|inspect\|reindex` | 管理 skill——列表、安装、启用/禁用、检查 |
 
-### 命令概览
+### 个性人格（Souls）
 
-```text
-codemini [prompt]
-codemini chat [prompt]
-codemini run <task>
-codemini config set|get|list <key> [value]
-codemini doctor
-codemini skill list|install|enable|disable|inspect|reindex
+CodeMini CLI 支持可切换的 "soul" 人格，仅改变语气和表达风格，不影响计划逻辑或代码行为。
+
+内置人格：`default`、`professional`、`ceo`、`playful`、`anime`、`caveman`、`pirate`
+
+```bash
+codemini config set soul.preset playful
 ```
 
 ### 工具模型怎么设计
 
 CodeMini CLI 把工具分成两层：
 
-- 默认工具
-  永远可见，覆盖最常见的编码主路径
-- 延迟工具
-  只有在需要时才通过 `tool_search` 加载
+- **默认工具** — 永远可见，覆盖最常见的编码主路径
+- **延迟工具** — 只有在需要时才通过 `tool_search` 加载
 
 这样做的目标，是让主界面更小、更稳，也让模型在第一反应时更容易走对路径。
 
-典型流程通常是：
+典型流程：
 
 1. `query_project_index` 或 `list` 做定位
 2. `read` 和 `grep` 做理解
@@ -267,18 +270,37 @@ CodeMini CLI 把工具分成两层：
 5. `update_todos` 追踪复杂任务
 6. 真的需要专门能力时，再 `tool_search`
 
+### 核心能力
+
+- 默认主工具保持在高频主路径：
+  - `read`、`grep`、`glob`、`list`、`query_project_index`
+  - `edit`、`write`
+  - `read_plan`、`update_plan`、`update_todos`
+  - `run`、`tool_search`
+- 更专业的能力按需加载：
+  - AST 工具：`ast_query`、`read_ast_node`
+  - 后台任务管理工具
+  - 持久 memory 工具
+- 通过 `update_todos` 维护复杂单任务的会话级待办清单，并直接渲染在 TUI 中
+- 统一的 shell 执行模型：
+  - 一次性命令直接 `run`
+  - 长运行命令通过 `run` + `run_in_background=true`
+- 在 `.codemini-project/` 下维护轻量项目索引，帮助模型更快理解仓库
+- 基于 Tree-sitter 的结构化编辑能力，适合函数级、类级、方法级改动
+- 支持通过 `ui.reply_language` 控制回复语言
+- safe mode 默认开启
+
 ### 项目索引
 
 CodeMini CLI 会在 `.codemini-project/` 下维护一份轻量项目索引：
 
-- `project-map.json`
-  记录仓库的高层结构事实，比如语言、源码目录、测试目录、入口候选
-- `file-index.json`
-  记录文件级结构信息，比如 imports、exports、functions、classes 和轻量 symbol 提示
+- `project-map.json` — 记录仓库的高层结构事实，比如语言、源码目录、测试目录、入口候选
+- `file-index.json` — 记录文件级结构信息，比如 imports、exports、functions、classes 和轻量 symbol 提示
 
 这份索引会在进入项目时初始化，在 `edit`、`write`、`patch` 后做增量刷新。它的目标是轻量、可靠、低噪声，而不是生成一份很长的 AI 报告。
 
-### 数据目录
+<details>
+<summary>数据目录与配置路径</summary>
 
 - 全局会话状态：`<base-config-dir>/sessions/`
 - 项目工作区状态：`.codemini/`
@@ -289,17 +311,15 @@ CodeMini CLI 会在 `.codemini-project/` 下维护一份轻量项目索引：
 
 `base-config-dir` 的解析顺序：
 
-- `CODEMINI_GLOBAL_DIR`
-- Windows：`%APPDATA%\codemini-global\`
-- macOS：`~/Library/Preferences/codemini-global`
-- Linux / XDG：`$XDG_CONFIG_HOME/codemini-global`
-- 受限环境回退：`.codemini-global/`
+| 平台 | 路径 |
+|------|------|
+| `CODEMINI_GLOBAL_DIR` 环境变量 | `$CODEMINI_GLOBAL_DIR`（最高优先级） |
+| Windows | `%APPDATA%\codemini-global\` |
+| macOS | `~/Library/Preferences/codemini-global` |
+| Linux / XDG | `$XDG_CONFIG_HOME/codemini-global` |
+| 受限环境回退 | `.codemini-global/` |
 
-### 文档入口
-
-- 操作手册与工作流说明：[OPERATIONS.md](./OPERATIONS.md)
-- 打包与部署文档：[deployment.md](./deployment.md)
-- 发布流程：[RELEASE_CHECKLIST.md](./RELEASE_CHECKLIST.md)
+</details>
 
 ### 适合谁
 
@@ -310,3 +330,26 @@ CodeMini CLI 会在 `.codemini-project/` 下维护一份轻量项目索引：
 - 真正重视 Windows / PowerShell 体验的终端工作流
 - 能把计划、待办、工具调用和执行状态展示清楚的 TUI
 - 更偏结构化操作、而不是大量 shell 噪声的代码助手
+
+### 文档入口
+
+- 操作手册与工作流说明：[OPERATIONS.md](./OPERATIONS.md)
+- 打包与部署文档：[deployment.md](./deployment.md)
+- 更新日志：[Releases](https://github.com/havingautism/Codemini-CLI/releases)
+
+### 开发
+
+```bash
+# 安装依赖
+npm install
+
+# 运行测试
+npm test
+
+# 本地启动
+npm start
+```
+
+### 许可证
+
+[MIT](LICENSE)

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "codemini-cli",
-  "version": "0.3.7",
+  "version": "0.3.8",
   "description": "Coding CLI optimized for small-model workflows and Windows PowerShell",
   "keywords": [
     "cli",

package/src/commands/chat.js

@@ -106,5 +106,29 @@ export async function handleChat(args) {
     })
   );
 
+  // Patch Ink's renderInteractiveFrame to never use clearTerminal.
+  // Ink calls clearTerminal (ESC[2J + ESC[H]) when the output frame exceeds
+  // the terminal viewport height, which resets the scroll position to the top
+  // and prevents the user from scrolling freely during streaming.
+  // By always using incremental logUpdate updates instead, old content scrolls
+  // into the terminal's scrollback naturally and the user can scroll freely.
+  const origRenderFrame = instance.renderInteractiveFrame;
+  instance.renderInteractiveFrame = function (output, outputHeight, staticOutput) {
+    const hasStaticOutput = staticOutput !== '';
+    const outputToRender = output + '\n';
+
+    if (hasStaticOutput) {
+      this.fullStaticOutput += staticOutput;
+      this.log.clear();
+      this.options.stdout.write(staticOutput);
+      this.log(outputToRender);
+    } else if (output !== this.lastOutput || this.log.isCursorDirty()) {
+      this.throttledLog(outputToRender);
+    }
+    this.lastOutput = output;
+    this.lastOutputToRender = outputToRender;
+    this.lastOutputHeight = outputHeight;
+  };
+
   await instance.waitUntilExit();
 }

package/src/commands/run.js

@@ -10,10 +10,10 @@ import fs from 'node:fs/promises';
 import path from 'node:path';
 
 const ROLE_TOOL_POLICY = {
-  planner: ['read', 'grep', 'list', 'query_project_index', 'tool_search', 'glob', 'ast_query', 'read_ast_node'],
-  coder: ['read', 'grep', 'list', 'edit', 'write', 'run', 'ast_query', 'read_ast_node', 'glob', 'tool_search', 'update_todos'],
-  reviewer: ['read', 'grep', 'list', 'glob', 'tool_search', 'ast_query', 'read_ast_node'],
-  tester: ['read', 'grep', 'list', 'run', 'glob', 'tool_search']
+  planner: ['read', 'grep', 'list', 'query_project_index', 'tool_search', 'glob', 'ast_query', 'read_ast_node', 'read_plan', 'update_plan'],
+  coder: ['read', 'grep', 'list', 'edit', 'write', 'run', 'ast_query', 'read_ast_node', 'glob', 'tool_search', 'update_todos', 'read_plan', 'update_plan'],
+  reviewer: ['read', 'grep', 'list', 'glob', 'tool_search', 'ast_query', 'read_ast_node', 'read_plan'],
+  tester: ['read', 'grep', 'list', 'run', 'glob', 'tool_search', 'read_plan']
 };
 const HARNESS_ROLES = Object.keys(ROLE_TOOL_POLICY);
 

package/src/core/agent-loop.js

@@ -247,6 +247,9 @@ function compactToolResult(result, toolName, args, maxChars = 12000) {
   if ('newTodos' in obj && Array.isArray(obj.newTodos)) {
     return obj.newTodos.length > 0 ? `updated ${obj.newTodos.length} todo item(s)` : 'cleared todo list';
   }
+  if ('newPlan' in obj) {
+    return obj.newPlan ? `updated plan state (${String(obj.newPlan.status || 'draft')})` : 'cleared plan state';
+  }
 
   // Fallback: clip with reduced limit
   return clipToolResult(obj, Math.min(maxChars, 4000));
@@ -358,7 +361,8 @@ export function checkReadDedup(filePath, startLine, endLine, mtimeMs) {
 const READ_ONLY_TOOLS = new Set([
   'read', 'grep', 'glob', 'list',
   'ast_query', 'read_ast_node',
-  'list_background_tasks', 'get_background_task'
+  'list_background_tasks', 'get_background_task',
+  'read_plan'
 ]);
 
 // ─── Exported helpers ────────────────────────────────────────────────
@@ -456,6 +460,9 @@ export function summarizeToolResult(result) {
     if ('newTodos' in obj && Array.isArray(obj.newTodos)) {
       return obj.newTodos.length > 0 ? `updated ${obj.newTodos.length} todo item(s)` : 'cleared todo list';
     }
+    if ('newPlan' in obj) {
+      return obj.newPlan ? `updated plan state (${String(obj.newPlan.status || 'draft')})` : 'cleared plan state';
+    }
     const keys = Object.keys(obj);
     return keys.length > 0 ? `keys: ${keys.slice(0, 5).join(',')}` : 'object';
   }
@@ -659,6 +666,9 @@ function formatToolDisplayName(name, args) {
   if (name === 'update_todos') {
     return 'update_todos';
   }
+  if (name === 'read_plan' || name === 'update_plan') {
+    return name;
+  }
   if (name === 'list_background_tasks') {
     return name;
   }