文档Docs
Bots 配置参考Bots configuration reference
按想做的事查 Bots 商用设置：额度、备用模型、保留期、引用来源、网站挂件，以及 Jev 审核对客服的影响。Find the Bots business settings by task: limits, backup models, retention, source links, the website widget, and how Jev review affects your bots.
这一页按你想做的事查 Bots 的商用设置。怎么新建 bot、选模型账户、接 Telegram，看让你的 bot 接待访客；每个配置项的默认值和可调范围，看那一页的商用配置参考。
两种改法
- 自己在手机上改：打开 设置 → Bots / 客服，选中这个 bot。额度在限额里，改完点「保存限额」；备用模型、话术、保留期和挂件在「商用配置：备用模型、话术和挂件」里。
- 让 Agent J 帮你改：直接说你的要求。Agent J 先看完整的配置说明，保留你现有的设置，再把修改发到已配对的手机，你签名后才生效。Agent 不能自己批准，修改里也不会放任何 key。
所有设置都存在你的 Agent J 主机上。
额度：多接待还是少接待
默认比较保守：每位访客每天 20 条、每个 bot 每天 100 条、整台主机每天合计 100 条，模型和安全审核合计每天 10 万 token；每位访客每分钟 6 条，单条最多 2000 字，同时接待 4 位访客。这些都能调高或调低，单条最多可以放到 4000 字。
模型调用结果不明时，预扣的额度不退回，免得少算费用。额度用完时访客看到的那句话可以改，见下面的话术。
备用模型：主模型出错时换一个
主模型后面最多再排两个备用模型，一共三个，按顺序尝试。备用模型从自带 key 支持的那十家按量服务商里选；每个备用都要在密钥卡里单独添加这个 bot 自己的 key，不借用主 Agent 的 key。三个都答不了时，可以给访客附上最多六个文档链接。
额度不够、安全审核拒绝或权限不允许时，不会换模型硬答。备用模型也会产生费用，算在对应的 key 上。
保留期：聊天留多久
聊天记录、访客身份和计数只存在你的 Agent J 主机上，默认保留 30 天，可以设 1 到 3650 天，每小时清理一次。模型回答时默认只回看 24 小时内、最多 40 条消息，这两个数也能改。
引用来源：回答附上原文链接
「回答附资料原文链接」默认打开，回答会附上检索到的资料的原文地址。从网址导入的资料会记住原地址；本地文件只有在你给了 HTTPS 来源地址时才附链接，不会编造链接。
资料源可以设成每天或每周自动刷新。主机在线、bot 启用时才刷新；刷新失败就保留上一份。访客不能让 bot 去抓任意网址。
话术和下班时间
欢迎语、离题回复、转人工、暂时不可用、下班和额度用完，这六句话都能改，每句最多 1000 字，可以中英文分开写。
下班后三选一：默认礼貌拒绝；也可以让 AI 照常回答，但不用任何工具；或者只收留言并通知你，不调用模型，留言也算额度。
网站挂件：一行代码放到自己的网站
- 在「允许嵌入的网站（https origin，逗号分隔）」里填你网站的完整 HTTPS 地址，比如
https://www.example.com。 - 点「复制嵌入代码」，把这一行贴进你的网页。它长这样（
data-bot是你的 bot 公开名字）：
<script src="https://agentj.app/bots/embed.js" data-bot="your-bot-name" async></script>网页角落会出现一个悬浮按钮，访客点开是一个竖长的聊天窗，手机上是浮窗。收起或按 Esc 不会丢掉对话。聊天在一个隔离的加密窗口里进行，你的网站本身拿不到消息内容。按钮的位置和颜色、欢迎语、最多六个快捷问题、要不要自动展开，都能在商用配置里改。第一次打开时，访客仍要信任网页加载的程序。
访客等回答时可以接着打字。「等待时排队合并」默认打开：排队的几段合成一条发出，只算一条消息；排着的内容可以撤回再改。
访客隐私和危险内容
访客消息在存下来之前，会去掉能认出来的密钥和卡号。但不是所有秘密都认得出，别让访客发密码。「拦截危险命令」默认打开，回答里的破坏性命令、下载后直接执行的命令会被拦下。网页回答里可以点的链接只限你填的域名，其他链接显示成文字。
转人工和邮件回复
访客要找人时，你默认可以在 48 小时内在聊天里回复，访客要在线才收得到。要用邮件回复，先配好 Agent J 邮件，再在商用配置里打开邮件转人工：访客留下邮箱，你核对地址后签名发一封验证码邮件（10 分钟有效，错 5 次锁定）；访客填对后，你逐封核对收件人和正文、签名发送。每个会话最多三封，验证码那封也算，失败不会自动重发。
Jev 审核对客服的影响
所有 bot 都跟着 设置 → 安全 里的 Jev 总开关走，三种选择的区别见 Jev 安全选项。
- 开着（TypeSafe 或 OpenRouter）：访客的问题和 bot 的回答，包括你的人工回复，发出前都过 Jev。缺 key 或审核失败时，bot 不发出回复，也不会改用别的账户。
- 你签名关闭后：不再找 Jev 审核，客服照样回答。本地的凭据过滤、危险命令拦截、权限和工具限制都还在。
- 还没选、也没有 key：bot 不能上线。
商用配置里的判据可以选普通客服或严格模式，严格模式还会拒绝超出你业务范围的问题。
This page finds the Bots business settings by what you want to do. To create a bot, choose its model account or connect Telegram, see Serve visitors with your bot. For every setting's default and range, see that page's commercial configuration reference.
Two ways to change settings
- On your phone: open Settings → Bots / Customer service and select the bot. Change quotas under the limits and tap "Save limits". Backup models, messages, retention and the widget are under "Business settings: fallback models, messages and widget".
- Ask Agent J: say what you want. Agent J reads the full settings description, keeps your current settings, and sends the change to your paired phone. It takes effect only after you sign it. The Agent cannot approve its own change, and a change never contains a key.
All settings stay on your Agent J host.
Limits: serve more or fewer visitors
The defaults are cautious: 20 messages per visitor per day, 100 per bot per day, 100 per day across the whole host, and 100,000 tokens per day for models and safety reviews together. Each visitor can send 6 messages per minute, a message holds up to 2000 characters, and 4 visitors are served at once. You can raise or lower all of them; a message can go up to 4000 characters.
When a model call ends with unknown usage, the reserved amount is not given back, so costs are never under-counted. You can change what visitors see when a limit is reached; see messages below.
Backup models: switch when the main model fails
Up to two backup models can follow the main model, three in total, tried in order. Backups use the same ten pay-as-you-go providers as your own model key. Each backup needs its own key for this bot, added through the secret card; it never borrows your main Agent's key. If all three fail, visitors can get up to six documentation links.
A spent budget, a safety refusal or a permission refusal never makes the bot switch models to answer anyway. Backup models cost money too, billed to their own keys.
Retention: how long chats are kept
Chats, visitor identities and counters stay only on your Agent J host. They are kept for 30 days by default, adjustable from 1 to 3650 days, and cleaned every hour. By default the model looks back over the last 24 hours and at most 40 messages; you can change both.
Source links: answers cite the original
"Append source links" is on by default: answers include the original address of the material they used. Material imported from a web address remembers that address. A local file gets a link only if you give it an HTTPS source address; no link is ever invented.
Sources can refresh daily or weekly. They refresh only while the host is online and the bot is enabled; if a refresh fails, the previous copy stays. Visitors cannot make the bot fetch any address they like.
Messages and after hours
You can rewrite six messages: welcome, off-topic, handed to a person, temporarily unavailable, after hours and limit reached. Each holds up to 1000 characters and can have separate Chinese and English text.
After hours, pick one: politely refuse (the default); let the AI answer without any tools; or only take a message and notify you without calling a model. Messages left this way count toward the limits.
Website widget: one line on your own site
- Under "Allowed embedding websites (HTTPS origins, comma separated)", enter your site's full HTTPS address, such as
https://www.example.com. - Tap "Copy embed code" and paste the line into your page. It looks like this (
data-botis your bot's public name):
<script src="https://agentj.app/bots/embed.js" data-bot="your-bot-name" async></script>A floating button appears in a corner of the page. Visitors tap it to open a tall chat window, or a floating sheet on phones. Closing it or pressing Esc keeps the conversation. The chat runs in an isolated, encrypted window; your website itself never receives the messages. The button's position and colour, the welcome text, up to six quick questions and whether it opens on load are all in the business settings. On first visit, visitors still have to trust the code the page loads.
Visitors can keep typing while they wait. "Merge queued messages" is on by default: queued text goes out as one message and counts once, and visitors can take queued text back to edit it.
Visitor privacy and dangerous content
Before visitor messages are stored, recognisable keys and card numbers are removed. Not every secret can be recognised, so never ask visitors for passwords. "Block dangerous commands" is on by default: destructive commands and download-and-run commands in answers are stopped. On the website, only links to the domains you list are clickable; other links show as plain text.
Handing over to you, and email replies
When a visitor asks for a person, you can reply in the chat for 48 hours by default; the visitor has to be online to receive it. To reply by email, set up Agent J mail first, then turn on handoff email in the business settings. The visitor leaves an address; you check it and sign a verification-code email (valid for 10 minutes, locked after 5 wrong tries). Once the visitor enters the code, you check the recipient and text of each email and sign it. At most three emails per conversation, the code email included; a failed send is never retried automatically.
How Jev review affects your bots
Every bot follows the Jev master switch in Settings → Safety. The three choices are explained in Jev safety options.
- On (TypeSafe or OpenRouter): visitor questions and bot answers, including your own replies, pass Jev before they go out. With a missing key or a failed review, the bot sends nothing and never switches to another account.
- Off, signed by you: no Jev review is requested and the bot keeps answering. Local credential filters, dangerous-command blocking, permissions and tool limits all stay.
- Nothing chosen and no key: the bot cannot go live.
In the business settings you can choose normal customer-service criteria or strict mode; strict also refuses questions outside your business.