# Release: datasette-agent 0.2a0
Source: [https://simonwillison.net/2026/Jun/10/datasette-agent/](https://simonwillison.net/2026/Jun/10/datasette-agent/)
Highlights from the release notes:
> - Tools can now ask the user questions mid\-execution\. Tools that declare a`context`parameter receive a`ToolContext`object, and`await context\.ask\_user\(\.\.\.\)`can ask a yes/no, multiple\-choice \(`options=\[\.\.\.\]`\) or free\-text \(`free\_text=True`\) question\. While a question is unanswered the agent turn suspends: the question renders as a form in the chat UI and persists to the internal database, so suspended conversations survive a server restart\. Once answered, the tool re\-executes from the top with stored answers replayed, so call`ask\_user\(\)`before performing side effects\.[\#20](https://github.com/datasette/datasette-agent/pull/20) - New built\-in`save\_query`tool: the agent can save SQL it has written as a[Datasette stored query](https://docs.datasette.io/en/latest/sql_queries.html#saved-queries)\. Saving always requires human approval \- the agent shows the full SQL plus the proposed name, database and visibility, and nothing is stored until you click Yes\.[\#20](https://github.com/datasette/datasette-agent/pull/20)
The`ask\_user\(\)`feature was enabled by the new LLM alpha I[built yesterday](https://simonwillison.net/2026/Jun/9/claude-fable-5/#adding-features-to-datasette-agent-and-llm-using-claude-code)with the help of Claude Fable 5\.
Datasette Agent 0.3a0 adds an execute_write_sql tool that requests user approval before writing to a database, along with CLI enhancements and unsafe mode for auto-approval.
Datasette-Agent 0.1a3 is released with UI improvements including 'View SQL query' buttons, better handling of empty reasoning chunks, and improved truncated response display.
Simon Willison releases datasette-agent-edit 0.1a0, a base plugin for Datasette Agent that implements agentic text editing tools (view, str_replace, insert) reusable by other plugins.
Datasette 1.0a31 introduces the ability to execute write queries and save stored queries (renamed from canned queries) for users with appropriate permissions, enhancing data editing capabilities.