Reuse conversation cache when streaming edits (#30245)

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
50 changed files with 847 additions and 21557 deletions
+1
View File
@@ -466,6 +466,7 @@ impl CodegenAlternative {
prompt_id: None,
mode: None,
tools: Vec::new(),
tool_choice: None,
stop: Vec::new(),
temperature,
messages: vec![request_message],