teableio · HynLcc · Jul 3, 2026 · Jul 3, 2026
diff --git a/en/basic/admin-panel/ai-setting.mdx b/en/basic/admin-panel/ai-setting.mdx
@@ -17,7 +17,7 @@ Before you open the AI Settings page, make sure the following items are ready. S
 | Requirement | Required? | Notes |
 |------|------|------|
 | **Agent Runtime setup** | Required for AI Chat and App Builder | Used by AI Chat and App Builder |
-| **Custom provider** | Optional | Use for supported model calls |
+| **Custom provider** | Required when AI Chat or App Builder uses your own key (BYOK) | Use an **OpenAI Compatible** or **Anthropic** provider |
 | **OpenAI Realtime API Key** | Optional | Only needed if you want to enable **Voice input** in AI Chat |
 | **Public access** | Required for App Builder publishing and attachment access | Your **Teable instance** and **object storage (MinIO / S3)** must be publicly accessible |
 
@@ -44,7 +44,7 @@ Follow these four steps:
 
 ### Configure LLM API
 
-In **LLM API**, add or verify the model provider used by supported model calls. If you add a custom provider, add the models it supports and complete the model test.
+In **LLM API**, add or verify the model provider used by supported model calls. If **AI Chat** or **App Builder** uses your own key (BYOK), choose **OpenAI Compatible** or **Anthropic** as the provider type, add the models it supports, and complete the model test.
 
 ### Configure Recommended Models
 
@@ -58,7 +58,7 @@ This step decides which models users can choose from. Start with a clear primary
 
 ### Set chat model
 
-This step sets the default model for sidebar **AI Chat**. The model must come from the recommended model list, so if this step is disabled, the previous step is usually incomplete.
+This step sets the default model for sidebar **AI Chat**. The model must come from the recommended model list, so if this step is disabled, the previous step is usually incomplete. If **AI Chat** or **App Builder** uses your own key (BYOK), choose a tested **OpenAI Compatible** or **Anthropic** model.
 
 Choose a tested, stable model here.
 
@@ -70,7 +70,7 @@ You can adjust **Max session duration (seconds)** and **Session creates per minu
 
 ### Configure Agent Runtime and App Builder
 
-Self-hosted **AI Chat** and **App Builder** require Agent Runtime setup. Self-hosted Agent Runtime deployment is still in an early stage and can be complex. Contact Teable at **support@teable.ai** for deployment support.
+Self-hosted **AI Chat** and **App Builder** require Agent Runtime setup and a compatible chat model. When you use your own key (BYOK), the chat model must come from an **OpenAI Compatible** or **Anthropic** provider. Self-hosted Agent Runtime deployment is still in an early stage and can be complex. Contact Teable at **support@teable.ai** for deployment support.
 
 <Steps>
   <Step title="Confirm Agent Runtime status">

diff --git a/en/basic/admin-panel/overview.mdx b/en/basic/admin-panel/overview.mdx
@@ -24,7 +24,7 @@ After logging in as an administrator, click the "Admin Panel" button in the uppe
 - **[AI settings](/en/basic/admin-panel/ai-setting)** - Configure AI features and models
 - **[Automation management](/en/basic/admin-panel/automation-management)** - View automation run status and run history
 - **[Audit log](/en/basic/admin-panel/audit-log)** - Review recent instance activity and operation details
-- **[Sandbox Agent](/en/basic/admin-panel/sandbox-agent)** - Configure Sandbox Agent runtime limits and base snapshots
+- **[Sandbox Agent](/en/basic/admin-panel/sandbox-agent)** - Configure and manage Sandbox Agent
 
 ### Administrator Permissions
 

diff --git a/en/basic/admin-panel/sandbox-agent.mdx b/en/basic/admin-panel/sandbox-agent.mdx
@@ -1,6 +1,6 @@
 ---
 title: "Sandbox Agent"
-description: "Configure Sandbox Agent enablement scope, runtime limits, and base snapshots."
+description: "Configure and manage Sandbox Agent."
 ---
 
 {/* mintlify-resync: 2026-05-26 */}
@@ -10,21 +10,12 @@ Path: Admin Panel → Sandbox Agent
 
 The **Sandbox Agent** page contains **Settings** and **Sandboxes** tabs for configuring how AI Chat runs in sandboxes.
 
-## Enablement Scope
-
-In the **Settings** tab:
-
-1. Turn on **Enable Sandbox Agent**.
-2. Configure spaces in **Enabled Spaces**.
-3. To enable all spaces, use **Enable for All Spaces**.
-
 ## Runtime Limits
 
 Configure runtime limits in the **Settings** tab:
 
 | Setting | Description |
 |------|------|
-| **Models** | Configure available models for each agent type |
 | **Stream Idle Timeout** | Set when an idle stream is terminated |
 | **Idle Timeout** | Set when an inactive sandbox is recycled |
 | **Concurrent Chat Limit** | Set how many Agents each user can run at the same time. AI Chat and App Builder are both Agents |
@@ -33,20 +24,8 @@ Configure runtime limits in the **Settings** tab:
 | **Temporary Disk** | Set the ephemeral storage limit for each sandbox instance |
 | **Thinking Effort** | Set the default thinking effort for agents |
 
-Click **Save** after configuring the settings.
-
-## Base Snapshots
-
-Create and manage snapshots in **Base Snapshots**.
-
-- Use **Quick Setup** to complete **Import Skills**, **Chat Snapshot**, and **App Builder**.
-- Use **Create Snapshot** to customize Agent SDK, system tools, Skills, and custom apt packages.
-- After a snapshot status is **Ready**, it can be set as **Active**.
-
 ## Sandboxes Tab
 
-In the **Sandboxes** tab, view active sandboxes and session history.
-
-The list shows Sandbox ID, Provider, Status, Uptime, and Last Activity. When needed, follow the page prompts to destroy a sandbox.
+Use the **Sandboxes** tab to view and manage current sandbox sessions.
 
-To clean up multiple sandboxes, click **Batch destroy**. Teable destroys only sandboxes that match the current filters. The confirmation dialog shows the matched count and requires typing `DESTROY` before continuing. This action cannot be undone. Preview URLs for deployed apps will stop working until the app owner reopens the chat.
+Ending active sessions interrupts running Agent work or app previews. Follow the in-product confirmation prompts before continuing.
diff --git a/en/basic/ai/ai-chat.mdx b/en/basic/ai/ai-chat.mdx
@@ -94,7 +94,7 @@ Ask questions about data in the current table, for example:
 
 If the question involves multiple tables, use `@` to add the related tables or views to the conversation.
 
-In Grid view, you can also select rows, columns, a single cell, or a cell range, then use **Add to Chat** from the context menu. The selection appears as a chip in the input box, and clicking the chip highlights the related grid area again.
+In Grid view, you can also select rows, columns, a single cell, or a cell range, then use **Add to Chat** from the context menu. The selection appears as a chip in the input box, and clicking the chip highlights the related grid area again. Column chips use field names when available and shorten long selections after the first few names.
 
 ### Generate Temporary Charts or Report Previews
 

diff --git a/en/basic/ai/app-builder.mdx b/en/basic/ai/app-builder.mdx
@@ -220,7 +220,7 @@ For prompt patterns, build tips, rollback advice, and common troubleshooting, se
   </Accordion>
 
   <Accordion title="Where do I configure App Builder for Self-Hosted?">
-    If you are running Teable self-hosted, follow the setup on the [AI Settings](/en/basic/admin-panel/ai-setting) page. Agent Runtime deployment is still in an early stage and can be complex. Contact Teable at **support@teable.ai** for deployment support.
+    If you are running Teable self-hosted, follow the setup on the [AI Settings](/en/basic/admin-panel/ai-setting) page. If App Builder uses your own key (BYOK), the chat model must come from an **OpenAI Compatible** or **Anthropic** provider. Agent Runtime deployment is still in an early stage and can be complex. Contact Teable at **support@teable.ai** for deployment support.
 
     <Note>
     Before publishing, make sure both your Teable instance and object storage (MinIO / S3) are publicly accessible. If you are unsure, use **Test Public Access** on the [AI Settings](/en/basic/admin-panel/ai-setting) page.

diff --git a/en/basic/ai/custom-model.mdx b/en/basic/ai/custom-model.mdx
@@ -1,20 +1,10 @@
 ---
 title: Custom AI Model
-description: Add custom model providers for AI Fields, Automations, and other supported model calls.
+description: Add custom model providers for AI Fields, Automations, AI Chat, App Builder, and other supported AI features.
 ---
 
 <Tip>Available for Pro plan and above</Tip>
 
-<Note>
-Custom model configuration applies to features that use model calls, such as **AI Fields** and **Automations**.
-
-On June 24, 2026, Teable rebuilt **Agent Computer**, improving Cuppy's processing speed and long-task stability in **AI Chat** and **App Builder**. BYOK compatibility for the Agent Runtime is in progress.
-
-**We recommend using Teable Credits.** Teable Credits are currently offered at cost, with no middleman and no markup, giving you access to top-tier AI models at competitive pricing with the smoothest experience.
-</Note>
-
-After setup, the models you add can be used by supported model calling features in the current space.
-
 ## Where to Configure It
 
 1. Open the target space.
@@ -34,10 +24,14 @@ Under **AI Capabilities**, turn on what you need:
 - **AI Field**
 - **AI Chat**
 
-Enabling **AI Chat** only controls whether the chat feature is available in the space. BYOK compatibility for the Agent Runtime is in progress.
+Enabling **AI Chat** controls whether the chat feature is available in the space.
 
 ### Add LLM Provider
 
+<Note>
+When **AI Chat** or **App Builder** uses a custom model, choose a provider whose type is **OpenAI Compatible** or **Anthropic**. If a task uses images, screenshots, or other visual input, choose a model with vision support. Models without vision support will fail on these multimodal tasks. Other provider types can still be used for supported features such as **AI Fields** and **Automations**.
+</Note>
+
 Click **Add LLM provider** and fill in the following:
 
 - **Name**: Used to distinguish different providers.
@@ -66,8 +60,6 @@ If a model is meant for image generation, check **Image Generation Model** befor
 
 ### Base URL
 
-<Warning>Use the API endpoint URL, not the provider's website URL. Most OpenAI-compatible endpoints need to end with `/v1`. Unless the provider's documentation explicitly says otherwise, do not add an extra trailing `/`.</Warning>
-
 <Warning>Some Coding Plan keys may only work in designated coding tools and may not be standard API keys. Check the provider's terms before using them with third-party services. To connect Teable, use a standard API key created in the provider dashboard.</Warning>
 
 Common Base URL examples for supported model calls:

diff --git a/zh/basic/admin-panel/ai-setting.mdx b/zh/basic/admin-panel/ai-setting.mdx
@@ -17,7 +17,7 @@ description: "为私有化部署实例配置 AI 对话、AI 字段、AI 自动
 | 准备项 | 是否必需 | 说明 |
 |------|------|------|
 | **Agent Runtime 配置** | AI 对话和应用构建器必需 | 用于 AI 对话和应用构建器 |
-| **自定义服务商** | 可选 | 用于已支持的模型调用 |
+| **自定义服务商** | AI 对话或应用构建器使用自带 Key 时必需 | 提供商类型选择 **OpenAI Compatible**（OpenAI 兼容）或 **Anthropic** |
 | **OpenAI Realtime API Key** | 可选 | 只有需要在 AI 对话中启用 **语音输入** 时才需要 |
 | **公网访问** | 应用发布和附件访问必需 | **Teable 实例** 和 **对象存储（MinIO / S3）** 需要被公网访问 |
 
@@ -44,7 +44,7 @@ description: "为私有化部署实例配置 AI 对话、AI 字段、AI 自动
 
 ### 配置 LLM API
 
-在 **LLM API** 中添加或确认已支持的模型调用所使用的模型服务商。如果添加自定义服务商，请填入它支持的模型，并完成模型测试。
+在 **LLM API** 中添加或确认已支持的模型调用所使用的模型服务商。如果 **AI 对话** 或 **应用构建器** 使用自带 Key，请将提供商类型选为 **OpenAI Compatible**（OpenAI 兼容）或 **Anthropic**，填入它支持的模型，并完成模型测试。
 
 ### 配置推荐模型
 
@@ -58,7 +58,7 @@ description: "为私有化部署实例配置 AI 对话、AI 字段、AI 自动
 
 ### 设置聊天模型
 
-这里要为侧边栏 **AI 对话** 指定默认模型。这个模型需要从推荐模型列表中选择，所以如果这一步是灰的，通常说明前一步还没完成。
+这里要为侧边栏 **AI 对话** 指定默认模型。这个模型需要从推荐模型列表中选择，所以如果这一步是灰的，通常说明前一步还没完成。**AI 对话** 或 **应用构建器** 使用自带 Key 时，请选择已测试通过的 **OpenAI Compatible**（OpenAI 兼容）或 **Anthropic** 模型。
 
 这里建议选择已经完成测试、表现稳定的模型。
 
@@ -70,7 +70,7 @@ description: "为私有化部署实例配置 AI 对话、AI 字段、AI 自动
 
 ### 配置 Agent Runtime 与应用构建器
 
-私有化部署如需使用 **AI 对话** 和 **应用构建器**，需要先完成 Agent Runtime 配置。Agent Runtime 的私有化部署仍处于早期阶段，配置流程较繁琐；请联系 Teable：**support@teable.ai**，获取部署协助。
+私有化部署如需使用 **AI 对话** 和 **应用构建器**，需要先完成 Agent Runtime 配置，并配置兼容的聊天模型。使用自带 Key 时，聊天模型必须来自 **OpenAI Compatible**（OpenAI 兼容）或 **Anthropic** 类型的提供商。Agent Runtime 的私有化部署仍处于早期阶段，配置流程较繁琐；请联系 Teable：**support@teable.ai**，获取部署协助。
 
 <Steps>
   <Step title="确认 Agent Runtime 状态">

diff --git a/zh/basic/admin-panel/overview.mdx b/zh/basic/admin-panel/overview.mdx
@@ -30,7 +30,7 @@ description: "Teable 私有化部署的管理员后台，用于管理实例的
 - **[AI 配置](/zh/basic/admin-panel/ai-setting)** - 配置 AI 功能和模型
 - **[自动化管理](/zh/basic/admin-panel/automation-management)** - 查看自动化运行状态和历史记录
 - **[审计日志](/zh/basic/admin-panel/audit-log)** - 查看近期实例活动和操作详情
-- **[沙箱 Agent](/zh/basic/admin-panel/sandbox-agent)** - 配置沙箱 Agent 运行限制和基础快照
+- **[沙箱 Agent](/zh/basic/admin-panel/sandbox-agent)** - 配置和管理沙箱 Agent
 
 ### 管理员权限
 

diff --git a/zh/basic/admin-panel/sandbox-agent.mdx b/zh/basic/admin-panel/sandbox-agent.mdx
@@ -1,6 +1,6 @@
 ---
 title: "沙箱 Agent"
-description: "配置沙箱 Agent 的启用范围、运行限制和基础快照。"
+description: "配置和管理沙箱 Agent。"
 ---
 
 {/* mintlify-resync: 2026-05-26 */}
@@ -10,21 +10,12 @@ description: "配置沙箱 Agent 的启用范围、运行限制和基础快照
 
 **沙箱 Agent** 页面包含 **设置** 和 **沙箱** 两个页签，用于配置 AI 对话的沙箱运行方式。
 
-## 启用范围
-
-在 **设置** 页签中：
-
-1. 打开 **启用沙箱 Agent**。
-2. 在 **已启用的空间** 中配置可使用沙箱 Agent 的空间。
-3. 如需对全部空间启用，可使用 **对所有空间启用**。
-
 ## 运行限制
 
 在 **设置** 页签中配置运行限制：
 
 | 设置 | 说明 |
 |------|------|
-| **模型** | 配置每个 Agent 类型可选的模型列表 |
 | **流式空闲超时** | 设置流式空闲后的终止时间 |
 | **空闲超时** | 设置沙箱无活动后的回收时间 |
 | **同时聊天上限** | 设置每个用户可同时运行的 Agent（AI 对话和应用构建器）数量 |
@@ -33,20 +24,8 @@ description: "配置沙箱 Agent 的启用范围、运行限制和基础快照
 | **临时盘** | 设置每个沙箱实例的临时存储上限 |
 | **思考深度** | 设置 Agent 默认思考深度 |
 
-配置完成后点击 **保存**。
-
-## 基础快照
-
-在 **基础快照** 区域创建和管理快照。
-
-- 使用 **快速设置** 按向导完成 **导入技能**、**Chat 快照** 和 **App Builder 快照**。
-- 使用 **创建快照** 自定义 Agent SDK、系统工具、Skills 和自定义 apt 包。
-- 快照状态为 **就绪** 后，可将其设为 **活跃**。
-
 ## 沙箱页签
 
-在 **沙箱** 页签中查看活跃沙箱和会话历史。
-
-列表中可查看沙箱 ID、提供商、状态、运行时间和最后活动时间。必要时可按页面提示销毁沙箱。
+在 **沙箱** 页签中查看并管理当前沙箱会话。
 
-如需批量清理，点击 **批量销毁**。系统只会销毁当前筛选范围内的沙箱。确认弹窗会显示匹配数量，输入 `DESTROY` 后才能继续。该操作不可撤销，已部署 app 的预览 URL 会中断，直到 app 拥有者重新唤起会话。
+结束活跃会话会中断正在运行的 Agent 任务或应用预览。继续前，请按页面提示确认。
diff --git a/zh/basic/ai/ai-chat.mdx b/zh/basic/ai/ai-chat.mdx
@@ -94,7 +94,7 @@ AI 不只回答问题，也可以协助创建、更新或整理数据。对于
 
 如果问题涉及多个表格，建议用 `@` 把相关表格或视图加入对话。
 
-在表格视图中，你也可以选中行、列、单个单元格或单元格区域，然后从右键菜单选择 **添加到 AI 对话**。选区会以标签形式进入输入框；点击标签时，会重新高亮对应的表格区域。
+在表格视图中，你也可以选中行、列、单个单元格或单元格区域，然后从右键菜单选择 **添加到 AI 对话**。选区会以标签形式进入输入框；点击标签时，会重新高亮对应的表格区域。列选区标签会优先显示字段名；列数较多时，只显示前几个字段名和剩余数量。
 
 ### 生成临时图表或报告预览
 

diff --git a/zh/basic/ai/app-builder.mdx b/zh/basic/ai/app-builder.mdx
@@ -235,7 +235,7 @@ Teable 自动跟踪每一次部署。
   </Accordion>
 
   <Accordion title="私有化部署需要在哪里配置应用构建器？">
-    如果您使用私有化部署的 Teable，请参考 [AI 配置](/zh/basic/admin-panel/ai-setting) 页面完成配置。Agent Runtime 的私有化部署仍处于早期阶段，配置流程较繁琐；请联系 Teable：**support@teable.ai**，获取部署协助。
+    如果您使用私有化部署的 Teable，请参考 [AI 配置](/zh/basic/admin-panel/ai-setting) 页面完成配置。如需让应用构建器使用自带 Key，聊天模型必须来自 **OpenAI Compatible**（OpenAI 兼容）或 **Anthropic** 类型的提供商。Agent Runtime 的私有化部署仍处于早期阶段，配置流程较繁琐；请联系 Teable：**support@teable.ai**，获取部署协助。
 
     <Note>
     发布前，请先确认 Teable 和对象存储（MinIO / S3）都能被公网访问；不确定时，可以在 [AI 配置](/zh/basic/admin-panel/ai-setting) 页面使用 **测试公网访问** 进行验证。