chore: fix closing error (#3709)

# What does this PR do?
Gets rid of this error message below (disclaimer: not sure why, but it
does).

ERROR 2025-10-06 12:04:22,837 asyncio:118 uncategorized: Task exception
was never retrieved
future: <Task finished name='Task-36' coro=<AsyncClient.aclose() done,
defined at

/Users/erichuang/projects/llama-stack-git2/.venv/lib/python3.12/site-packages/httpx/_client.py:1978>
exception=RuntimeError('unable to perform operation on <TCPTransport
closed=True reading=False 0x122dc7ad0>; the handler is closed')>
╭───────────────────────────────────────────────────────────────────
Traceback (most recent call last)
───────────────────────────────────────────────────────────────────╮
│
/Users/erichuang/projects/llama-stack-git2/.venv/lib/python3.12/site-packages/httpx/_client.py:1985
in aclose │
│ │
│ 1982 │ │ if self._state != ClientState.CLOSED: │
│ 1983 │ │ │ self._state = ClientState.CLOSED │
│ 1984 │ │ │ │
│ ❱ 1985 │ │ │ await self._transport.aclose() │
│ 1986 │ │ │ for proxy in self._mounts.values(): │
│ 1987 │ │ │ │ if proxy is not None: │
│ 1988 │ │ │ │ │ await proxy.aclose() │
│ │
│
/Users/erichuang/projects/llama-stack-git2/.venv/lib/python3.12/site-packages/httpx/_transports/default.py:406
in aclose │
│ │
│ 403 │ │ ) │
│ 404 │ │
│ 405 │ async def aclose(self) -> None: │
│ ❱ 406 │ │ await self._pool.aclose() │
│ 407 │
│ │
│
/Users/erichuang/projects/llama-stack-git2/.venv/lib/python3.12/site-packages/httpcore/_async/connection_pool.py:353
in aclose │
│ │
│ 350 │ │ with self._optional_thread_lock: │
│ 351 │ │ │ closing_connections = list(self._connections) │
│ 352 │ │ │ self._connections = [] │
│ ❱ 353 │ │ await self._close_connections(closing_connections) │
│ 354 │ │
│ 355 │ async def __aenter__(self) -> AsyncConnectionPool: │
│ 356 │ │ return self │
│ │
│
/Users/erichuang/projects/llama-stack-git2/.venv/lib/python3.12/site-packages/httpcore/_async/connection_pool.py:345
in _close_connections │
│ │
│ 342 │ │ # Close connections which have been removed from the pool. │
│ 343 │ │ with AsyncShieldCancellation(): │
│ 344 │ │ │ for connection in closing: │
│ ❱ 345 │ │ │ │ await connection.aclose() │
│ 346 │ │
│ 347 │ async def aclose(self) -> None: │
│ 348 │ │ # Explicitly close the connection pool. │
│ │
│
/Users/erichuang/projects/llama-stack-git2/.venv/lib/python3.12/site-packages/httpcore/_async/connection.py:173
in aclose │
│ │
│ 170 │ async def aclose(self) -> None: │
│ 171 │ │ if self._connection is not None: │
│ 172 │ │ │ async with Trace("close", logger, None, {}): │
│ ❱ 173 │ │ │ │ await self._connection.aclose() │
│ 174 │ │
│ 175 │ def is_available(self) -> bool: │
│ 176 │ │ if self._connection is None: │
│ │
│
/Users/erichuang/projects/llama-stack-git2/.venv/lib/python3.12/site-packages/httpcore/_async/http11.py:258
in aclose │
│ │
│ 255 │ │ # Note that this method unilaterally closes the connection,
and does │
│ 256 │ │ # not have any kind of locking in place around it. │
│ 257 │ │ self._state = HTTPConnectionState.CLOSED │
│ ❱ 258 │ │ await self._network_stream.aclose() │
│ 259 │ │
│ 260 │ # The AsyncConnectionInterface methods provide information about
the state of │
│ 261 │ # the connection, allowing for a connection pooling
implementation to │
│ │
│
/Users/erichuang/projects/llama-stack-git2/.venv/lib/python3.12/site-packages/httpcore/_backends/anyio.py:53
in aclose │
│ │
│ 50 │ │ │ │ await self._stream.send(item=buffer) │
│ 51 │ │
│ 52 │ async def aclose(self) -> None: │
│ ❱ 53 │ │ await self._stream.aclose() │
│ 54 │ │
│ 55 │ async def start_tls( │
│ 56 │ │ self, │
│ │
│
/Users/erichuang/projects/llama-stack-git2/.venv/lib/python3.12/site-packages/anyio/streams/tls.py:216
in aclose │
│ │
│ 213 │ │ │ │ await aclose_forcefully(self.transport_stream) │
│ 214 │ │ │ │ raise │
│ 215 │ │ │
│ ❱ 216 │ │ await self.transport_stream.aclose() │
│ 217 │ │
│ 218 │ async def receive(self, max_bytes: int = 65536) -> bytes: │
│ 219 │ │ data = await
self._call_sslobject_method(self._ssl_object.read, max_bytes) │
│ │
│
/Users/erichuang/projects/llama-stack-git2/.venv/lib/python3.12/site-packages/anyio/_backends/_asyncio.py:1310
in aclose │
│ │
│ 1307 │ │ if not self._transport.is_closing(): │
│ 1308 │ │ │ self._closed = True │
│ 1309 │ │ │ try: │
│ ❱ 1310 │ │ │ │ self._transport.write_eof() │
│ 1311 │ │ │ except OSError: │
│ 1312 │ │ │ │ pass │
│ 1313 │
│ │
│ in uvloop.loop.UVStream.write_eof:703 │
│ │
│ in uvloop.loop.UVHandle._ensure_alive:159 │

╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
RuntimeError: unable to perform operation on <TCPTransport closed=True
reading=False 0x122dc7ad0>; the handler is closed

## Test Plan
Run
uv run --with llama-stack llama stack build --distro=starter
--image-type=venv --run

No more error

llama_stack/providers/utils/inference/openai_mixin.py

@@ -132,7 +132,10 @@ class OpenAIMixin(NeedsRequestProviderData, ABC, BaseModel):
 
         :return: An iterable of model IDs or None if not implemented
         """
-        return [m.id async for m in self.client.models.list()]
+        client = self.client
+        async with client:
+            model_ids = [m.id async for m in client.models.list()]
+        return model_ids
 
     async def initialize(self) -> None:
         """