Adam Perry @ OpenAI 58b66d39e4 perf(skills): resolve plugin namespaces per root (#31348) ...

## Why

Loading skills from a remote executor can add a lot to thread start time
when there are many skills. Previous changes added some concurrency for
the file reads themselves, but we're still bottlenecked on the initial
root path discovery.

Using the benchmark from
[#31295](https://github.com/openai/codex/pull/31295), this change
reduces the measured mean of loading 66 skills about 71%. Behavioral
coverage lands separately in
[#31369](https://github.com/openai/codex/pull/31369).

## What

- resolve the scanned root's inherited namespace once
- resolve discovered nested plugin roots once, retaining
nearest-valid-ancestor behavior
- pass an explicit resolved Plain / Plugin namespace into skill parsing
instead of probing per skill
- preserve explicitly provided plugin namespaces as the highest-priority
source
- reuse the same resolver for environment skills, deleting its duplicate
root-probe and ancestor-selection path

## Validation

- just test -p codex-core-skills namespace: 12 passed on both the parent
and optimized branches

2026-07-07 23:00:15 +00:00

..

src

perf(skills): resolve plugin namespaces per root (#31348)

2026-07-07 23:00:15 +00:00

tests

Overlap executor skill reads with namespace discovery (#30225)

2026-06-26 18:37:59 +00:00

BUILD.bazel

build: run buildifier from just fmt (#28125)

2026-06-13 21:43:39 -07:00

Cargo.toml

config: own layer provenance types (#29722)

2026-06-24 04:03:04 +00:00