Yehowshua/ZIm
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Reuse conversation cache when streaming edits (#30245)

Browse source 
Release Notes:

- Improved latency when the agent applies edits.
This commit is contained in:
Antonio Scandurra 2025-05-08 14:36:34 +02:00 • committed by GitHub
parent 032022e37b
commit 9f6809a28d
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
50 changed files with 847 additions and 21557 deletions
Download patch file Download diff file Expand all files Collapse all files

7
crates/language_models/src/provider/mistral.rs
View file

@ -10,7 +10,8 @@ use http_client::HttpClient;
use language_model::{
AuthenticateError, LanguageModel, LanguageModelCompletionError, LanguageModelCompletionEvent,
LanguageModelId, LanguageModelName, LanguageModelProvider, LanguageModelProviderId,
LanguageModelProviderName, LanguageModelProviderState, LanguageModelRequest, RateLimiter, Role,
LanguageModelProviderName, LanguageModelProviderState, LanguageModelRequest,
LanguageModelToolChoice, RateLimiter, Role,
};
use futures::stream::BoxStream;
@ -302,6 +303,10 @@ impl LanguageModel for MistralLanguageModel {
false
}
fn supports_tool_choice(&self, _choice: LanguageModelToolChoice) -> bool {
false
}
fn telemetry_id(&self) -> String {
format!("mistral/{}", self.model.id())
}