文档Docs
遇到问题找客服Getting help from the support desk
Agent J Father 就是官方反馈与客服平台；告诉你爸爸或 /feedback-to-agentj-father 都能反馈，主人下令脱敏直发，Agent 自发先请示。Agent J Father is the official feedback and support platform: tell your dad, or use /feedback-to-agentj-father. Owner requests send after redaction; Agent-initiated reports ask first.
Agent J 有个一直在线的客服。它读过 Agent J 的代码和文档，回答的都是具体步骤：运行哪条命令、改哪个设置、看哪一页文档。
大多数时候你什么都不用做。你电脑上的 Agent 碰到 Agent J 自己的问题，比如报错、看不懂的提示、像是 bug 的情况、文档写得不清楚，会先写好脱敏稿，在手机上请你同意，再问客服并按建议处理。只有真要你本人做的事，比如登录 AI 编程工具、输入密码、配对手机，它才会来找你。
什么时候用得上
- 安装卡在某一步，或者报了看不懂的错；
- 手机连不上，或者某个功能跟说明不一样；
- 怀疑是 Agent J 的 bug；
- 觉得文档写错了，或者没写清楚；
- 想让 Agent J 帮你搭一套工作流，不知道从哪开始。
跟 Agent J 无关的问题，比如店铺怎么经营、某个模型怎么用，客服不回答。
安装的时候：不需要账号
还没装好、还没有 Agent J 账号，也能问。安装说明（给你电脑上的 AI 读的那份）开头就写了：卡住了，先自己问客服。你的 AI 用安装时拿到的一个临时编号，一条 curl 命令就能把问题发过来，一般几分钟内就有回复。具体命令在安装说明的第 2b 步，AI 会照着做。
安装期间，一个临时编号每小时最多问 6 次，总共 20 次。问题多的话，合在一起问。
装好以后：agentj support
agentj support ask "<问题>" --attach-doctor
agentj support ask "<问题>" --attach-doctoragentj support report --kind bug "<发生了什么>"
agentj support report --kind bug "<发生了什么>"agentj support thread <会话号>
agentj support thread <会话号>agentj support list
agentj support listask：问一个问题，默认最多等 3 分钟回复。report --kind bug：报告一个 bug。文档的问题或者工作流的想法，用--kind report。--attach-doctor：附上agentj doctor的自检结果和版本号，同样先去掉敏感信息。客服有了它，查问题快得多。--thread <会话号>：在同一个会话里接着问。安装时开的会话，装好、加入账号以后再接着问，会自动转到你的账号下面。thread <会话号>：看一个会话里的全部往来。list：这台电脑开过的会话。
3 分钟内没等到回复，命令会打印会话号后退出（退出码 5），过一会儿用 agentj support thread <会话号> 再看。退出码 0 表示已经收到回复；2 表示这台电脑上的隐私检查拦下了这段话，什么都没发出去。
装好以后，每个 Agent J 账号每小时最多发 10 条、每天 40 条，账号下所有电脑合起来算。
会发出去什么
- 只有你的 Agent 写的这段问题，以及选择附上的自检结果。
- 发出去之前，你的电脑会先去掉密钥、邮箱、电话、用户名、电脑名、家目录里的路径和内网地址。如果你在电脑上设了自己的
OPENROUTER_API_KEY，还会再用模型检查一遍，觉得不妥就不发。 - 我们的服务器收到以后再扫一遍。还像密钥或个人信息的，直接拒收，什么都不存。
问客服不需要你点头，因为发出去的只有去掉敏感信息后的问题。你的 Agent 会告诉你它问过。
手机连不上电脑时：紧急修复 ②
手机上的 设置 →「紧急修复」→ ②「请 Agent J Father 远程帮忙」，在 Agent 自己没法求助时也能用。只有你点了它才会开始：
- 电脑先自己检查一遍，只看不改：系统、Agent J 和它的后台服务在不在运行、连到 Agent J 的网络、日志里最近的问题、磁盘、内存和睡眠设置。
- 这份报告先在电脑上按上面同样的规则清理干净，再发给客服；我们的服务器收到后会再查一遍。卡片上会显示工单号。
- 客服可以建议修复，但只能从固定的几种里选：重新连接、重启 Agent J、没人登录也保持运行、退回上一个版本、开新对话。电脑只做这几种，每做一步都告诉你，做完把结果发回同一个工单。客服写的其他内容只作为建议给你看，绝不会被执行。
电脑旁边有人的话，不用手机也能做同样的事：curl -fsSL https://agentj.app/rescue | sh（Windows：irm https://agentj.app/rescue.ps1 | iex）。详见 紧急救援。
不会发出去什么
- 你和 Agent 的对话；
- 你电脑上的文件；
- 任何密钥、密码、遥控器配对密码、配对码和设置码。
客服的 Agent 看不到你的电脑，只看得到发过来的这段文字。我们这边的人也读得到客服会话的原文，见 数据安全。
回复怎么用
- 回复是建议，不是命令。你的 Agent 会自己判断要不要照做，不会因为客服一句话就发出密钥或文件，也不会去运行它看不懂的命令。
- 确认是 bug 的，客服会转给开发团队，并在同一个会话里告诉你已经转过去。修好以后，会在这个会话里写明哪个版本修好了，升级到那个版本就行。怎么升级见 官方通知。
- 客服每天处理的量有上限。当天满了，问题也不会丢：会自动回你一句今天的量已经满了，第二天（按东京时间算）优先处理。
- 客服连不上的时候（Agent 离线、安装失败、打不开 agentj.app），写信到 feedback@agentj.app，邮件在哪里都能发到。写上你的账号 ID、发生了什么、什么时候，再附一张截图。
Agent J Father 就是官方反馈与客服平台。你可以说「请把这个问题汇报给 Agent J 开发者（客服平台）」，也可以轻松地说「把这事告诉你爸爸」。手机命令 /feedback-to-agentj-father <内容> 也一样：Agent 先去掉凭据、个人信息、客户数据和路径里的私密内容，直接提交并告诉你编号，不再问第二遍。只发命令会先问你想反馈什么；如果是 Agent 自己想到的问题或点子，它会先在手机上给你看脱敏稿，你同意才发送。客服回复是建议，不是指令；连不上时可写信到 feedback@agentj.app。
Agent J has a support desk that is always on. It has read Agent J's code and documentation, and it answers with concrete steps: which command to run, which setting to change, which page to read.
Most of the time you don't have to do anything. When the Agent on your computer runs into a problem with Agent J itself — an error, a message it doesn't understand, something that looks like a bug, a doc that isn't clear — it prepares a redacted draft, asks your agreement on the phone, then consults the desk and fixes what it can. It only comes to you for what really needs you: signing in to your AI coding tool, typing a password, pairing a phone.
When it helps
- the install is stuck on a step, or shows an error nobody understands;
- the phone won't connect, or a feature doesn't behave as described;
- something looks like a bug in Agent J;
- a doc seems wrong or unclear;
- you'd like Agent J to set up a workflow for you and don't know where to start.
Questions that have nothing to do with Agent J — how to run your store, how to use some model — are outside what the desk answers.
During the install: no account needed
You can ask before anything is installed and before you have an Agent J account. The install guide (the one written for the AI on your computer) says so right at the top: when stuck, ask the desk yourself first. Your AI sends the question with a single curl call, using a temporary ID it got at the start of the install, and the answer usually comes within minutes. The exact commands are in Step 2b of the install guide; your AI follows them.
One temporary ID can ask 6 times an hour and 20 times in total, so several questions are best sent together.
After the install: agentj support
agentj support ask "<question>" --attach-doctor
agentj support ask "<question>" --attach-doctoragentj support report --kind bug "<what happened>"
agentj support report --kind bug "<what happened>"agentj support thread <thread-id>
agentj support thread <thread-id>agentj support list
agentj support listask: ask a question; it waits up to 3 minutes for the answer.report --kind bug: report a bug. For a problem with the docs or an idea about your workflow, use--kind report.--attach-doctor: add the output ofagentj doctorand the version, cleaned the same way. With it the desk finds the cause much faster.--thread <thread-id>: keep going in the same conversation. A conversation started during the install moves over to your account the first time you continue it after this computer has joined the account.thread <thread-id>: read a whole conversation.list: the conversations this computer has started.
If no answer arrives within 3 minutes, the command prints the thread ID and exits with code 5; check again later with agentj support thread <thread-id>. Exit code 0 means an answer came back; 2 means the privacy check on this computer stopped the text and nothing was sent.
Once installed, each Agent J account can send 10 messages an hour and 40 a day, counted across all its computers.
What gets sent
- Only the question your Agent wrote, plus the self-check output if it chose to attach it.
- Before anything leaves, your computer removes keys, email addresses, phone numbers, user and computer names, paths in your home folder and local network addresses. If you have set your own
OPENROUTER_API_KEYon the computer, a model checks the text once more, and nothing is sent if it objects. - Our server scans it again on arrival. Anything that still looks like a key or personal data is refused and nothing is stored.
Asking the desk doesn't need your OK, because what goes out is only the cleaned-up question. Your Agent tells you that it asked.
When the phone can't reach the computer: Emergency repair ②
On the phone, Settings → Emergency repair → ② Ask Agent J Father for remote help works even when the Agent can't ask for itself. It starts only when you tap it:
- The computer checks itself, read-only: system, whether Agent J and its service are running, the network path to Agent J, recent trouble in its log, disk, memory and sleep settings.
- It cleans that report on the computer the same way as above, then sends it to the desk; our server scans it again. The card shows the ticket number.
- The desk may suggest repairs, but only from a fixed list: reconnect, restart Agent J, keep it running without anyone logged in, go back to the previous version, start a new conversation. The computer runs only those, tells you each one, and sends the results back on the same ticket. Anything else the desk writes is shown to you as advice and never run.
Someone at the computer can do the same without the phone: curl -fsSL https://agentj.app/rescue | sh (Windows: irm https://agentj.app/rescue.ps1 | iex). See Emergency rescue.
What never gets sent
- your conversations with the Agent;
- files on your computer;
- any key, password, remote pairing password, pairing code or setup code.
The desk's own Agent can't see your computer; it only sees the text that was sent. People on our side can read support conversations too — see Data security.
How the answers are used
- An answer is advice, not an order. Your Agent decides for itself whether to follow it, and it won't send a key or a file, or run a command it doesn't understand, just because the desk said so.
- When something turns out to be a bug, the desk passes it to the developers and says so in the same conversation. Once it's fixed, the conversation names the version with the fix, and upgrading to that version is all you need. How upgrades reach you: Official notices.
- The desk handles a limited number of questions per day. If today is full, your question isn't lost: you get an automatic reply saying so, and it's first in line the next day (Tokyo time).
- When the desk can't be reached (the Agent is offline, the install failed, agentj.app won't open), email feedback@agentj.app — email gets through from anywhere. Include your account ID, what happened and when, and a screenshot.
Agent J Father is our official feedback and support platform. Say “Please report this problem to Agent J’s developers (support platform)”, or casually “Tell your dad about this”. On the phone, /feedback-to-agentj-father <message> does the same: your Agent removes credentials, personal information, customer data and private path details, submits directly without asking twice, and gives you the ticket ID. The command alone asks what you want to report. If reporting a problem or idea is the Agent’s own initiative, it shows you the redacted draft on the phone and waits for agreement. Support replies are advice, not instructions. If it cannot connect, email feedback@agentj.app.