Datasette Agent 0.1a9 Update Adds Default Model Support
Current overview (not historical)
Simon Willison released datasette-llm 0.1a9, a plugin update that allows Datasette Agent to automatically read the default LLM model without explicit configuration. Previously, users had to specify the model via the flag -s plugins.datasette-agent.default_model gpt-6-astra. This version removes that explicit dependency, simplifying the default model usage process.
Written with AI from the reporting · updated 11/1/2026
Expand the detailed fact route and sources
Story route
A station-by-station route from the first public evidence onward; every station carries its own evidence and uncertainty.
- 1Unclassified fact stationNov 1, 00:00recorded Nov 1, 08:23single sourcerevised
Datasette Agent 0.1a9 更新支持默认模型
Read original source ↗ Simon WillisonReplay this moment in the explorerEvidence & revisions · 1 source records
- Subject：
- datasette-llm
- Action：
- 更新插件以自动使用 LLM 的默认模型
- Object：
- LLM 默认模型配置
- Occurred (fact side)：
- Nov 1, 00:00
- Published (valid side)：
- Nov 1, 06:10
- First seen (known side)：
- Nov 1, 08:23
Fact stationSingle source · one-sided claimRevisedCopy may have been revised later; time replay is bounded. Layer labels group reading only, not causation between layers.
Uncertainty marks flag where to check the sources; they are not proven causation.
Report timeline
Explore every side through dated source reports.
- Simon WillisonRelated fact: single sourceSource report revisedDatasette Agent 0.1a9 released with automatic model detection
Report first recorded Nov 1, 08:23
The datasette-llm plugin version 0.1a9 now automatically picks up the default model configured for the LLM tool, allowing users to start Datasette Agent without explicitly setting a default model. Previously, users had to specify the model using the setting plugins.datasette-agent.default_model gpt-6-astra.
Read original source ↗
Event activity trend
- Latest comparable
- 3
- Comparable peak
- 9Nov 1, 09:00
- 24h change
- -50%
The chart compares consistently observed participants only. Hover or tap to inspect each hour; use arrow keys to move between observations.
Event discussion
Reader opinions are hosted on GitHub Discussions; posting requires a GitHub account. Comments are not verified facts.