mirror of
https://github.com/openai/codex.git
synced 2026-11-13 14:46:14 +00:00
Move host skill prompt injection into the skills extension (#37503)
## What changed - Add `HostSkillsSnapshot::load_skill_prompts` so the skills extension owns reading and rendering selected host skills. - Keep explicit invocation telemetry, unreadable-skill warnings, plugin prompt ordering, and suppression of host prompts superseded by provider prompts. - Remove the legacy prompt injection and fragment implementation from `codex-core-skills`. ## Testing - Cover prompt truncation without an installed skills extension, skill/plugin ordering, selective provider supersession, unreadable skills, and contextual fragment detection. GitOrigin-RevId: 9c8b84ad54b90d174abc287ab49cc5a231e9e1aa
This commit is contained in:
1 parent
8e4b10446e
commit
beac16cccd
22 files changed
+553
-299
No files matched your search
@@ -384,6 +384,9 @@ pub(crate) struct SkillsTurnState {
|
||||
pub(crate) main_prompts_injected: bool,
|
||||
}
|
||||
|
||||
#[derive(Clone, Copy, Debug, Default, PartialEq, Eq)]
|
||||
pub(crate) struct HostSkillsCatalogInWorldState;
|
||||
|
||||
#[derive(Clone, Debug, Default)]
|
||||
pub(crate) struct ExecutorSkillsStepState(pub(crate) SkillCatalog);
|
||||
|
||||
|
||||
Reference in new issue
Block a user