mirror of
https://github.com/openai/codex.git
synced 2026-11-20 22:40:37 +00:00
## What changed - Add an opt-in `skill_search` feature that ranks prompt-visible skills against each turn's user input with a bounded weighted lexical selector. - Keep the ranked selection out of model-visible context and record metrics for selection cost, catalog reduction, and whether later implicit or `skills.read` invocations matched the ranked candidates. - Include host-provided skills in the experiment catalog without changing the rendered skill catalog. ## Testing - Add selector unit tests covering ranking, limits, truncation, stop words, and deterministic tie-breaking. - Add extension tests covering turn-local invocation recording and host-skill shadow selection. GitOrigin-RevId: 4d00a1c805ea8b391d6c6ac6a8450afa88ca3e25
25 lines
610 B
Rust
25 lines
610 B
Rust
pub mod catalog;
|
|
mod config;
|
|
mod dynamic_skill_selector;
|
|
mod extension;
|
|
mod fragments;
|
|
pub mod provider;
|
|
mod render;
|
|
mod selection;
|
|
mod shadow_selection_experiment;
|
|
mod sources;
|
|
mod state;
|
|
mod tools;
|
|
mod world_state;
|
|
|
|
pub use config::SkillsExtensionConfig;
|
|
pub use extension::install;
|
|
pub use extension::install_with_providers;
|
|
pub use extension::install_with_providers_and_metrics;
|
|
pub use provider::ExecutorSkillProvider;
|
|
pub use provider::HostSkillProvider;
|
|
pub use provider::OrchestratorSkillProvider;
|
|
pub use provider::SkillProvider;
|
|
pub use sources::SkillProviderSource;
|
|
pub use sources::SkillProviders;
|