项目文件夹

文件

T

文件历史

Simon Willison ee2ffbec23 Tool implementations can receive the ToolCall via llm_tool_call parameter

Tool functions (sync or async, including Toolbox methods) that declare
a parameter named llm_tool_call are now passed the llm.ToolCall object
for the current invocation. The parameter is reserved: it is excluded
from the input schema exposed to the model and is only injected when
declared explicitly - a **kwargs catch-all does not receive it.

This lets tool implementations key external state against the unique
tool_call_id, e.g. for human-in-the-loop approval flows that need to
resume a specific tool call after the answer arrives.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

2026-06-09 13:01:39 -07:00

default_plugins

--hide-reasoning and hide_reasoning=True parameters (#1442 )

2026-05-12 09:24:51 -07:00

__init__.py

Do not have xPart classes as llm. imports

2026-04-28 16:44:21 -07:00

__main__.py

Rename back to llm, refs #1

2023-04-01 15:00:19 -07:00

cli.py

--hide-reasoning and hide_reasoning=True parameters (#1442 )