datasette-agent 0.2a0 Introduces Interactive User Questioning for Tools
English summary
Version 0.2a0 of datasette-agent is released. Tools can now ask user questions mid-execution using await context.ask_user(...), supporting yes/no, multiple-choice, or free-text input. The question renders as a form in the chat UI and persists to the internal database, so suspended conversations survive a server restart; the tool re-executes from the top once answered. A built-in save_query tool saves SQL as a Datasette stored query, but requires explicit human approval with full SQL, name, database, and visibility displayed before storage. This release was built on a new LLM alpha developed with Claude Fable 5.
Chinese summary
datasette-agent 0.2a0 版本发布。工具现可通过 await context.ask_user(...) 在执行中向用户提问，支持是/否、多选和自由文本三种形式。问题在聊天界面中以表单呈现，并持久化到内部数据库，暂停的对话在服务器重启后依然存在；用户回答后，工具会从开头重新执行。新增内置 save_query 工具，可将 SQL 保存为 Datasette 存储查询，但必须经人工审核——会展示完整 SQL、名称、数据库和可见性，用户点击确认后才存储。此版本基于一个用 Claude Fable 5 构建的新 LLM 阿尔法版开发。
Key points
Tools can now interrupt execution to ask the user yes/no, multiple-choice, or free-text questions via ask_user().
工具现可在执行中暂停，通过 ask_user() 向用户提出是/否、多选或自由文本问题。
Unanswered questions persist to the internal database, enabling conversations to survive server restarts; the tool re-executes once the answer is provided.
未回答的问题持久化到内部数据库，对话可在服务器重启后继续；回答后工具从头重新执行。
A new save_query tool saves SQL as a stored query, requiring human approval with full SQL and metadata shown before saving.
新增 save_query 工具保存 SQL 为存储查询，但需展示完整 SQL 与元数据并获用户批准后才能保存。
Built on a new LLM alpha created with Claude Fable 5.
基于用 Claude Fable 5 构建的新 LLM 阿尔法版开发。