mirror of
https://github.com/openai/codex.git
synced 2026-08-23 13:09:46 +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Keep explicit invocation telemetry, unreadable-skill warnings, plugin prompt ordering, and suppression of host prompts superseded by provider prompts.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:
6
codex-rs/Cargo.lock
generated
6
codex-rs/Cargo.lock
generated
@@ -2911,16 +2911,10 @@ dependencies = [
|
||||
name = "codex-core-skills"
|
||||
version = "0.0.0"
|
||||
dependencies = [
|
||||
"codex-analytics",
|
||||
"codex-context-fragments",
|
||||
"codex-exec-server",
|
||||
"codex-otel",
|
||||
"codex-skills",
|
||||
"codex-utils-absolute-path",
|
||||
"codex-utils-path-uri",
|
||||
"codex-utils-string",
|
||||
"pretty_assertions",
|
||||
"tracing",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
|
||||
Reference in New Issue
Block a user