# Summary
Reduce download traffic to `github.com/openai/plugins` while continuing
to check for updates on every Codex startup.
# Root cause
The startup sync replaced the local repository with a fresh shallow
clone whenever the remote revision changed. At Codex's global scale,
repeatedly downloading the repository created excessive GitHub traffic.
# Changes
- Run `git ls-remote` on each startup to read the remote HEAD SHA.
- Skip all repository downloads when the local and remote SHAs match.
- Update existing checkouts with an exact-SHA shallow `git fetch`,
followed by reset and clean.
- Bootstrap new installations with `git init` plus the same shallow
fetch, rather than cloning.
- Keep the existing file lock so concurrent Codex processes serialize
updates and do not duplicate fetches.
- Preserve the existing GitHub HTTP and export archive fallback
behavior.
# Impact
Each startup makes one lightweight remote HEAD check. Repository objects
are downloaded only when the revision changes, and existing Git objects
are reused during updates.
# Validation
- `just test -p codex-core-plugins startup_sync` (15 tests passed)
- `just test -p codex-core-plugins` (201 tests passed)
- `just clippy -p codex-core-plugins` (passes with one pre-existing
`large_enum_variant` warning)
- Production app-server smoke test against GitHub:
- Fresh home: `ls-remote`, `git init`, one exact-SHA shallow fetch
- Unchanged restart: `ls-remote` and local `rev-parse` only; no fetch or
clone
- Bench smoke passed
beggers-openai ·
xl-openai ·