fix(ai): report ai sql action results and errors in pane

This commit is contained in:
Abeautifulsnow
2026-10-14 20:46:20 +08:00
committed by GitHub
parent f201de8f40
commit 5a67c5dbd6
24 changed files with 1097 additions and 52 deletions
+14
View File
@@ -169,6 +169,20 @@ Redis 连接改用只读命令工具,而不是 SQL。助手可以执行 DBX
<Callout type="info">AI Agent 不会获得“以后都可以写”的授权,也不会绕过 MCP 策略、连接只读保护或数据库权限。更多边界见 [生产环境安全](/cn/docs/production-safety)。</Callout>
## SQL 代码块操作
回复里的每个 SQL 代码块都提供 **临时运行**、**立即执行** 和 **应用到编辑器**。三者都作用于该对话**自己绑定**的连接、数据库和 Schema 对应的查询页签,而不是当前恰好在前台的那个编辑器。
该页签不存在时会在后台创建,动作本身也**不会移动你的工作区**:AI 动作不会自行切换、选中或打开任何页签。
正因为结果不总落在你眼前,代码块会自己报告结果:
* 块内显示 **执行中…**,结束后显示返回或影响的行数,失败则显示数据库返回的错误文本。
* 目标页签不在屏幕上时,提示会写明是哪个页签并提供 **查看**;只有点击 **查看** 才会切过去。
* 根本没跑起来的情况(没有可用连接、页签仍在处理上一个请求、没有可执行的 SQL)也会在块内说明原因。
危险 SQL、生产库、参数和只读解锁仍然使用各自的确认对话框,代码块和提示不会重复一遍。
## 推理强度和 Thinking
不同供应商使用不同机制:枚举 effort、reasoning level、布尔 thinking、整数预算或自定义文本。DBX 按当前模型能力展示可用选项,并记住每个配置/模型的选择。
+14
View File
@@ -171,6 +171,20 @@ Redis connections use a read-only command tool instead of SQL. The assistant can
<Callout type="info">AI Agent never receives “write from now on” permission and cannot bypass MCP policy, connection read-only protection, or database privileges. See [Production Safety](/en/docs/production-safety) for the complete boundary.</Callout>
## SQL Block Actions
Each SQL block in a reply offers **Temp run**, **Execute**, and **Apply to editor**. All three target the query tab that belongs to the conversation's own connection, database, and schema — the connection the conversation is bound to, never whichever editor happens to be in front.
That tab is created in the background when it does not exist yet, and the action never moves your workspace: an AI action does not switch, select, or open tabs on its own.
Because the result therefore does not always land where you are looking, the block reports its own outcome:
* The block shows **Executing…**, then the row count (returned or affected) or the database's error text.
* When the target tab is not on screen, a notification names that tab and offers **View**; only clicking **View** brings it to the front.
* Requests that never reached the database say why in the block instead: no available connection, an editor tab still busy with another request, or nothing to execute.
Dangerous-SQL, production, parameter, and read-only confirmations keep their own dialogs; those are not repeated in the block or as a notification.
## Reasoning Effort and Thinking
Providers expose different mechanisms: enumerated effort, reasoning levels, boolean thinking, integer budgets, or free-text options. DBX shows controls from the active model capability and remembers the selection per configuration and model.