Add props, slots, tokenize and the cache-loss check to the llama client

Implemented-By: OpenCode session (model recorded in docs/implementer-log.md)
2026-09-18 03:39:05 -07:00
parent 0fa481df29
commit 3663a1e4d5
4 changed files with 333 additions and 0 deletions
@@ -1,6 +1,7 @@
 //! The llama inference server's chat-completions types and the request builder.

 pub mod assemble;
+pub mod info;
 pub mod request;

 #[derive(Debug, Clone, PartialEq, Eq)]