valknar/llmx
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Improve gpt-oss compatibility (#2461)

Browse Source 
The gpt-oss models require reasoning with subsequent Chat Completions
requests because otherwise the model forgets why the tools were called.
This change fixes that and also adds some additional missing
documentation around how to handle context windows in Ollama and how to
show the CoT if you desire to.
This commit is contained in:
Dominik Kundel
2025-09-02 19:49:03 -07:00
committed by GitHub
parent a93a907c7e
commit b127a3643f
5 changed files with 886 additions and 26 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
codex-rs/core/src/lib.rs
View File

@@ -69,3 +69,14 @@ pub use codex_protocol::protocol;
// Re-export protocol config enums to ensure call sites can use the same types
// as those in the protocol crate when constructing protocol messages.
pub use codex_protocol::config_types as protocol_config_types;
pub use client::ModelClient;
pub use client_common::Prompt;
pub use client_common::ResponseEvent;
pub use client_common::ResponseStream;
pub use codex_protocol::models::ContentItem;
pub use codex_protocol::models::LocalShellAction;
pub use codex_protocol::models::LocalShellExecAction;
pub use codex_protocol::models::LocalShellStatus;
pub use codex_protocol::models::ReasoningItemContent;
pub use codex_protocol::models::ResponseItem;