perf(model-metadata): resolve localhost to IPv4 in detect_local_server_type

On Windows, `localhost` resolves to both ::1 (IPv6) and 127.0.0.1 (IPv4).
httpx tries IPv6 first, hanging 2 sec per probe when the server binds IPv4
only. detect_local_server_type() is called 3+ times during init, each with
a new httpx.Client, compounding to ~14s of dead time.

Replace localhost with 127.0.0.1 inside the function before connecting.
The function is only called for local endpoints (callers guard with
is_local_endpoint()), so IPv6 loopback adds no diagnostic value.

Measured: 19.9s → 4.0s on Windows with a local proxy on 127.0.0.1:8317.
This commit is contained in:
Rod Boev 2026-06-02 15:04:51 -04:00
parent 05cbddc012
commit a075d3194b
2 changed files with 66 additions and 0 deletions

View file

@ -636,6 +636,12 @@ def detect_local_server_type(base_url: str, api_key: str = "") -> Optional[str]:
server_url = server_url[:-3]
lmstudio_url = _lmstudio_server_root(base_url)
# Resolve localhost to IPv4 to avoid 2s IPv6 timeout on Windows dual-stack.
server_url = server_url.replace("://localhost:", "://127.0.0.1:")
server_url = server_url.replace("://localhost/", "://127.0.0.1/")
if server_url.endswith("://localhost"):
server_url = server_url[:-len("localhost")] + "127.0.0.1"
headers = _auth_headers(api_key)
try: