269 lines
7.9 KiB
Markdown
269 lines
7.9 KiB
Markdown
# openclaw-auto-continue
|
||
|
||
可重用的 OpenClaw skill，提供 `/auto-continue`（別名 `/ac`）的 session-level auto-followup 使用方式。
|
||
|
||
Reusable OpenClaw skill for `/auto-continue` (`/ac`) session-level auto-followup.
|
||
|
||
## 繁體中文說明
|
||
|
||
### 先看這裡：你要哪一種？
|
||
|
||
#### 1. 我只是要在已支援的 OpenClaw chat 裡使用 `/ac`
|
||
先看：
|
||
- `openclaw-auto-continue/SKILL.md`
|
||
|
||
用途：
|
||
- 什麼情況該開 `/ac`
|
||
- `/ac on` / `/ac off` / `/ac status` 怎麼用
|
||
- 使用邊界與 troubleshooting
|
||
|
||
#### 2. 我要讓另一台機器真的做出 `/ac` 指令
|
||
直接照做：
|
||
- `openclaw-auto-continue/references/installation-guide.md`
|
||
|
||
這份是 **end-to-end installation guide**，會帶你從：
|
||
- 找 live runtime
|
||
- 找 command handler
|
||
- 加 `/ac` / `/auto-continue`
|
||
- 寫入 session queue 設定
|
||
- 部署 / 重啟
|
||
- 真實 chat 驗證
|
||
一路做到完成
|
||
|
||
#### 3. 我不是要照做，我是要理解 runtime 接法與行為邏輯
|
||
看：
|
||
- `openclaw-auto-continue/references/runtime-integration.md`
|
||
|
||
用途：
|
||
- 看 handler 應該做什麼
|
||
- 看 `status / on / off` 的語意
|
||
- 看 integration / troubleshooting 重點
|
||
|
||
### 這個 repo 內有什麼
|
||
- `openclaw-auto-continue/SKILL.md` — **給 Agent 看的** skill 指引
|
||
- `openclaw-auto-continue/references/installation-guide.md` — **給要落地 `/ac` 指令的人 / agent 看** 的安裝指南
|
||
- `openclaw-auto-continue/references/runtime-integration.md` — `/ac` runtime integration 說明
|
||
- `openclaw-auto-continue.skill` — 已打包好的 skill 檔
|
||
|
||
### 其他電腦怎麼用
|
||
|
||
#### 方式 1：直接 clone repo
|
||
```bash
|
||
git clone https://gitea.cowbay.org/openclaw/openclaw-auto-continue.git
|
||
cd openclaw-auto-continue
|
||
```
|
||
|
||
把 skill 資料夾放到目標機器的 OpenClaw skills 目錄：
|
||
|
||
```bash
|
||
mkdir -p ~/.openclaw/workspace/skills
|
||
cp -R openclaw-auto-continue ~/.openclaw/workspace/skills/
|
||
```
|
||
|
||
#### 方式 2：直接用 `.skill` 檔
|
||
如果目標 OpenClaw 環境已有 skill 匯入 / 安裝流程，就直接使用：
|
||
|
||
- `openclaw-auto-continue.skill`
|
||
|
||
### 在目標 OpenClaw 聊天 / session 裡怎麼開
|
||
安裝 skill **不代表每個 chat 都會自動啟用**。
|
||
你還是要在想啟用的那個 chat / session 裡手動開：
|
||
|
||
```text
|
||
/ac on
|
||
```
|
||
|
||
查狀態：
|
||
|
||
```text
|
||
/ac status
|
||
```
|
||
|
||
關閉：
|
||
|
||
```text
|
||
/ac off
|
||
```
|
||
|
||
### `/ac on` 之後會發生什麼
|
||
開啟後，目前 session 會使用 followup 型續跑設定：
|
||
|
||
- `queueMode = "followup"`
|
||
- `queueDebounceMs = 0`
|
||
- `queueCap = 1`
|
||
- `queueDrop = "summarize"`
|
||
|
||
實際效果：
|
||
- agent 比較可能直接接著做下一個低風險步驟
|
||
- 比較不容易每做一步就停下來
|
||
- 適合在同一個 chat 中做多步任務
|
||
|
||
### 重要邊界
|
||
這是 **session-scoped**，不是全域開關。
|
||
如果你想在另一個 chat 生效，就要在那個 chat 再開一次。
|
||
|
||
它也**不會**繞過：
|
||
- approvals
|
||
- safety checks
|
||
- destructive action confirmation
|
||
- user decision points
|
||
|
||
### 如果其他電腦出現 `/ac` unknown
|
||
這通常代表目標機器的 **live OpenClaw runtime 還沒有真正實作這個 command**。
|
||
|
||
所以這個 repo 不只要教怎麼用，還要教怎麼把 `/ac` 接進 runtime。
|
||
請看：
|
||
|
||
- `openclaw-auto-continue/references/runtime-integration.md`
|
||
|
||
這份文件會說明：
|
||
- runtime handler 應該做什麼
|
||
- `/ac status`、`/ac on`、`/ac off` 應該如何改變 session
|
||
- 如何驗證另一台真實機器
|
||
- 如果 skill 存在但 command 不存在，應該怎麼排查
|
||
|
||
### 給 Agent 看
|
||
如果 OpenClaw agent 要判斷怎麼使用這個 repo：
|
||
|
||
1. 先讀 `openclaw-auto-continue/SKILL.md`
|
||
2. 如果目標機器不認得 `/ac`，再讀 `openclaw-auto-continue/references/runtime-integration.md`
|
||
3. 在對應 chat / session 中使用 `/ac on`、`/ac off`、`/ac status`
|
||
|
||
一句話：
|
||
- `README.md` 是給人 / operator 看的
|
||
- `openclaw-auto-continue/SKILL.md` 是給 agent 看的
|
||
- `references/installation-guide.md` 是給要從頭做到尾落地 `/ac` 的人 / agent 看的
|
||
- `references/runtime-integration.md` 是給要理解 runtime 接法的人 / agent 看的
|
||
|
||
---
|
||
|
||
## English
|
||
|
||
### Start here: which path do you need?
|
||
|
||
#### 1. I just want to use `/ac` in a chat where the runtime already supports it
|
||
Read first:
|
||
- `openclaw-auto-continue/SKILL.md`
|
||
|
||
Use this for:
|
||
- when `/ac` should be enabled
|
||
- how to use `/ac on` / `/ac off` / `/ac status`
|
||
- boundaries and troubleshooting
|
||
|
||
#### 2. I want another machine to actually implement the `/ac` command
|
||
Follow this directly:
|
||
- `openclaw-auto-continue/references/installation-guide.md`
|
||
|
||
This is the **end-to-end installation guide** that walks through:
|
||
- locating the live runtime
|
||
- finding the command handler
|
||
- adding `/ac` / `/auto-continue`
|
||
- writing session queue settings
|
||
- deploy / restart
|
||
- real chat verification
|
||
|
||
#### 3. I do not need step-by-step install; I need runtime design/integration details
|
||
Read:
|
||
- `openclaw-auto-continue/references/runtime-integration.md`
|
||
|
||
Use this for:
|
||
- handler behavior expectations
|
||
- `status / on / off` semantics
|
||
- integration and troubleshooting details
|
||
|
||
### What this repo contains
|
||
- `openclaw-auto-continue/SKILL.md` — the **agent-facing** skill instructions
|
||
- `openclaw-auto-continue/references/installation-guide.md` — end-to-end guide for making `/ac` real on another machine
|
||
- `openclaw-auto-continue/references/runtime-integration.md` — runtime integration notes for `/ac`
|
||
- `openclaw-auto-continue.skill` — packaged skill artifact
|
||
|
||
### For humans: how to use on another computer
|
||
|
||
#### Option 1: clone the repo
|
||
```bash
|
||
git clone https://gitea.cowbay.org/openclaw/openclaw-auto-continue.git
|
||
cd openclaw-auto-continue
|
||
```
|
||
|
||
Then copy the skill folder into the target machine's OpenClaw skills directory:
|
||
|
||
```bash
|
||
mkdir -p ~/.openclaw/workspace/skills
|
||
cp -R openclaw-auto-continue ~/.openclaw/workspace/skills/
|
||
```
|
||
|
||
#### Option 2: use the packaged `.skill` file
|
||
If your target OpenClaw environment already has a skill import/install flow, use:
|
||
|
||
- `openclaw-auto-continue.skill`
|
||
|
||
### On the target OpenClaw chat/session
|
||
Installing the skill does **not** automatically enable auto-continue for every chat.
|
||
You still need to turn it on in the specific chat/session where you want it active:
|
||
|
||
```text
|
||
/ac on
|
||
```
|
||
|
||
Check status:
|
||
|
||
```text
|
||
/ac status
|
||
```
|
||
|
||
Turn it off:
|
||
|
||
```text
|
||
/ac off
|
||
```
|
||
|
||
### What changes after `/ac on`
|
||
When enabled, the current session uses followup-style continuation behavior:
|
||
|
||
- `queueMode = "followup"`
|
||
- `queueDebounceMs = 0`
|
||
- `queueCap = 1`
|
||
- `queueDrop = "summarize"`
|
||
|
||
Practical effect:
|
||
- the agent is more likely to continue into the next low-risk step
|
||
- the agent is less likely to stop after every intermediate update
|
||
- this is good for multi-step execution in the same chat
|
||
|
||
### Important boundary
|
||
This is **session-scoped**, not global.
|
||
If you want it active in a different chat, enable it in that chat too.
|
||
|
||
It also does **not** bypass:
|
||
- approvals
|
||
- safety checks
|
||
- destructive action confirmation
|
||
- user decision points
|
||
|
||
### If another machine says `/ac` is unknown
|
||
That usually means the target machine's **live OpenClaw runtime does not actually implement the command yet**.
|
||
|
||
So this repo should teach not only usage, but also how to integrate `/ac` into the runtime.
|
||
See:
|
||
|
||
- `openclaw-auto-continue/references/runtime-integration.md`
|
||
|
||
That file explains:
|
||
- what the runtime handler must do
|
||
- what `/ac status`, `/ac on`, `/ac off` should change
|
||
- how to verify a real target machine
|
||
- how to troubleshoot a machine where the skill exists but the command does not
|
||
|
||
### For agents
|
||
If an OpenClaw agent is deciding how to use this repo:
|
||
|
||
1. Read `openclaw-auto-continue/SKILL.md`
|
||
2. If the target machine does not recognize `/ac`, read `openclaw-auto-continue/references/runtime-integration.md`
|
||
3. Use `/ac on`, `/ac off`, and `/ac status` in the relevant chat/session
|
||
|
||
In short:
|
||
- `README.md` is the human/operator guide
|
||
- `openclaw-auto-continue/SKILL.md` is the agent-facing guide
|
||
- `references/installation-guide.md` is for end-to-end `/ac` installation work
|
||
- `references/runtime-integration.md` is for runtime integration details
|