min-agent 0.7.8 → 1.0.0

package/README.md

@@ -64,7 +64,7 @@ Type `/` to open the command menu; **↑/↓** selects. On an empty input, **↑
 | `/memory` | Toggle memory or save a note |
 | `/undo` · `/diff` | Undo last turn · show changes so far |
 | `/attach` · `/mcp` · `/skills` | Attach an image · MCP servers · skills |
-| `/tokens` · `/help` | Usage & cost · all commands |
+| `/tokens` · `/help` | Usage, reuse & cost · all commands |
 
 Shortcuts: **Ctrl+C** clears input (press twice to exit) · **Shift+Enter** / **Ctrl+J** inserts a newline · **Ctrl+V** pastes an image · **Ctrl+B** copies selected text · click a tool or thinking block to expand it.
 
@@ -72,7 +72,7 @@ Shortcuts: **Ctrl+C** clears input (press twice to exit) · **Shift+Enter** / **
 
 File edits are auto-approved by default; risky actions always ask. When several actions in one step need approval, they're combined into a single prompt instead of a stack of separate ones. Each prompt offers 允许 / 总是允许 / 拒绝 — choosing 总是允许 remembers that action for the current session, so repeated identical commands or MCP tools won't ask again.
 
-`min-agent exec` (one-shot) runs more freely by default: edits and ordinary commands don't ask — only genuinely destructive commands (deleting files, dropping/truncating databases, disk-wiping, `git reset --hard`, etc.) still prompt. Pass `--permission` or `--yes` to override.
+`min-agent exec` (one-shot) runs more freely by default: edits and ordinary commands don't ask — only genuinely destructive commands (deleting files, dropping/truncating databases, disk-wiping, `git reset --hard`, etc.) still prompt. Pass `--permission` or `--yes` to override. Thinking and tool calls print as a single summary line each.
 
 ```bash
 min-agent permission                 # show current setting
@@ -111,7 +111,7 @@ Settings live in `~/.min-agent/config.json` (global). For per-project settings,
 
 - **MCP servers** — connect external tools: `min-agent mcp -h`
 - **Skills** — reusable instructions loaded automatically: `min-agent skills -h`
-- **Project rules** — add `AGENTS.md` or `RULES.md` to your project; global rules go in `~/.min-agent/rules.md`
+- **Project rules** — add `AGENTS.md` or `RULES.md` to your project; global rules go in `~/.min-agent/rules.md` or `~/.min-agent/AGENTS.md`
 
 ## API Access
 
@@ -168,7 +168,7 @@ min-agent --provider anthropic "..."   # 为一条消息指定服务商
 | `/memory` | 开关记忆，或保存一条 |
 | `/undo` · `/diff` | 撤销上一轮 · 查看已产生的改动 |
 | `/attach` · `/mcp` · `/skills` | 附加图片 · MCP 服务 · 技能 |
-| `/tokens` · `/help` | 用量与费用 · 全部命令 |
+| `/tokens` · `/help` | 用量、复用与费用 · 全部命令 |
 
 快捷键：**Ctrl+C** 清空输入（连按两次退出）· **Shift+Enter** / **Ctrl+J** 换行 · **Ctrl+V** 粘贴图片 · **Ctrl+B** 复制选中的文本 · 点击工具或思考块可展开收起。
 
@@ -176,7 +176,7 @@ min-agent --provider anthropic "..."   # 为一条消息指定服务商
 
 文件修改默认自动批准，危险操作仍会询问；同一步里有多个操作需要授权时，会合并成一个弹窗逐条列出，而不是弹出一堆。弹窗提供 允许 / 总是允许 / 拒绝 三个选项——选「总是允许」会在本次会话内记住该操作，之后重复的相同命令或 MCP 工具不再询问。
 
-`min-agent exec`（单次执行）默认更放手：文件修改和普通命令都不询问，只有真正具破坏性的命令（删除文件、drop/truncate 数据库、抹盘、`git reset --hard` 等）才会询问。加 `--permission` 或 `--yes` 可覆盖此默认。
+`min-agent exec`（单次执行）默认更放手：文件修改和普通命令都不询问，只有真正具破坏性的命令（删除文件、drop/truncate 数据库、抹盘、`git reset --hard` 等）才会询问。加 `--permission` 或 `--yes` 可覆盖此默认。思考过程和工具调用各占一行摘要，不展开全文。
 
 ```bash
 min-agent permission                 # 查看当前设置
@@ -217,7 +217,7 @@ min-agent setup      # 添加自己的服务商（交互式）
 
 - **MCP 服务**：连接外部工具与数据源，`min-agent mcp -h`
 - **技能（Skills）**：可自动加载的可复用指令集，`min-agent skills -h`
-- **项目规则**：在项目里添加 `AGENTS.md` 或 `RULES.md`；全局规则写入 `~/.min-agent/rules.md`
+- **项目规则**：在项目里添加 `AGENTS.md` 或 `RULES.md`；全局规则写入 `~/.min-agent/rules.md` 或 `~/.min-agent/AGENTS.md`
 
 ## API 接入