Hopiu/llm
1
0
Fork 0
mirror of https://github.com/Hopiu/llm.git synced 2026-03-16 20:50:25 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Removed some fluff from the changelog

Browse source 
!stable-docs
This commit is contained in:
Simon Willison 2025-05-26 00:40:47 -07:00 committed by GitHub
parent 15a497635d
commit 5a8d7178c3
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 2 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
docs/changelog.md
View file

@ -8,11 +8,11 @@ Hopefully the last alpha before a stable release that includes tool support.
### Features
* **Plugin-provided tools can now be grouped into "Toolboxes".**
* Toolboxes (`llm.Toolbox` classes) allow plugins to expose multiple related tools that share state or configuration, enhancing modularity and reusability (e.g., a `Memory` tool or `Filesystem` tool). ([#1059](https://github.com/simonw/llm/issues/1059), [#1086](https://github.com/simonw/llm/issues/1086))
* Toolboxes (`llm.Toolbox` classes) allow plugins to expose multiple related tools that share state or configuration (e.g., a `Memory` tool or `Filesystem` tool). ([#1059](https://github.com/simonw/llm/issues/1059), [#1086](https://github.com/simonw/llm/issues/1086))
* **Tool support for `llm chat`.**
* The `llm chat` command now accepts `--tool` and `--functions` arguments, allowing interactive chat sessions to use tools. ([#1004](https://github.com/simonw/llm/issues/1004), [#1062](https://github.com/simonw/llm/issues/1062))
* **Tools can now execute asynchronously.**
* Models that implement `AsyncModel` can now run tools, including tool functions defined as `async def`. This enables non-blocking tool calls for potentially long-running operations. ([#1063](https://github.com/simonw/llm/issues/1063))
* Models that implement `AsyncModel` can now run tools, including tool functions defined as `async def`. ([#1063](https://github.com/simonw/llm/issues/1063))
* **`llm chat` now supports adding fragments during a session.**
* Use the new `!fragment <id>` command while chatting to insert content from a fragment. Initial fragments can also be passed to `llm chat` using `-f` or `--sf`. Thanks, [Dan Turkel](https://github.com/daturkel). ([#1044](https://github.com/simonw/llm/issues/1044), [#1048](https://github.com/simonw/llm/issues/1048))
* **Filter `llm logs` by tools.**