ZIm/crates/language_model/src
Cole Miller ee6f834028
Fuse LLM completion stream to avoid a panic (#21914)
`LanguageModel::stream_completion_text` can poll the `stream_completion`
stream (ultimately a `futures::Unfold`) after it's returned
`Ready(None)`, which leads to a panic; avoid this by fusing the stream.

Release Notes:

- Fixed a panic when streaming language model completions
2024-12-12 11:39:35 -05:00
..
model Remove Qwen2 model (#18444) 2024-09-27 13:30:25 -04:00
fake_provider.rs Add language_models crate to house language model providers (#20945) 2024-11-20 18:49:34 -05:00
language_model.rs Fuse LLM completion stream to avoid a panic (#21914) 2024-12-12 11:39:35 -05:00
rate_limiter.rs Allow customization of the model used for tool calling (#15479) 2024-07-30 16:18:53 +02:00
registry.rs gpui: Don't export named Context from prelude (#21869) 2024-12-11 13:21:40 -05:00
request.rs assistant2: Restructure storage of tool uses and results (#21194) 2024-11-25 21:53:27 -05:00
role.rs Restructure workflow step resolution and fix inserting newlines (#15720) 2024-08-05 09:18:06 +02:00