Simon Willison
datasette-mcp 0.2
Read the original on Simon Willison →The Flow has not summarised this story yet — read it at Simon Willison.
Related stories
Simon Willison
6d ago
datasette-llm 0.1a9
The release of datasette-llm 0.1a9 introduces a small user‑experience improvement: the plugin now automatically detects the default LLM model, eliminating the need for users to manually configure a default model when running Datasette Agent. This change simplifies the setup process for users who previously had to specify a model with the `-s plugins.datasette-agent.default_model` option.
Simon Willison
Sep 20
datasette-explain 0.2.2
The article announces the release of datasette-explain version 0.2.2, noting that the plugin’s plan explanations now work on read‑only stored‑query pages. The author upgraded the demo site to Datasette 1.0a40, which motivated the new plugin version. The release is tagged for sqlite and datasette users.
Simon Willison
Aug 13
sqlite-utils 4.2
Release: sqlite-utils 4. 2 Lots of improvements in this one relating to the table.
Simon Willison
2d ago
datasette-llm 0.1a10
The article announces the release of datasette-llm version 0.1a10. It reports a bug fix that corrects the demo site at agent.datasette.io, ensuring that only LLM models specified in the configuration are available. The update addresses a configuration issue affecting model availability.
Simon Willison
Sep 16
datasette 1.0a40
The article announces the release of Datasette 1.0a40, which includes a security fix identical to that in version 0.65.5, new features such as the ability for plugins to launch and manage background tasks via the datasette.add_background_task() method, and a migration to httpx2 to support features like datasette.client.get(). The update also contains numerous bug fixes, many of which were addressed during a recent triage effort for the upcoming 1.0 stable release.
Simon Willison
Sep 22
llm 0.36
The release of llm 0.36 introduces new OpenAI models gpt-6-sol and gpt-6-luna, and adds support for model plugins to declare that they do not support conversations via supports_conversation = False. When such models receive assistant or tool history, llm raises a ConversationNotSupported error and the chat interface rejects them before starting a session. Additional changes include wrapping reasoning traces in Markdown output with <details> tags and bug fixes from five contributors.