Environment
- google-genai 2.24.0, google-auth 2.58.0, Python 3.12
- Vertex AI backend (
GOOGLE_GENAI_USE_VERTEXAI=true), service-account ADC
- Live API with many concurrent sessions per process (telephony voice agent)
What happens
On Vertex, AsyncLive.connect() (google/genai/live.py, ~L1055-1069) runs this before it opens the websocket:
if not self._api_client._credentials:
creds, _ = google.auth.default(scopes=[...]) # sync, on the event loop
else:
creds = self._api_client._credentials
if not (creds.token and creds.valid):
auth_req = _auth_requests().Request()
creds.refresh(auth_req) # sync HTTP, on the event loop
Two problems:
- Blocking I/O inside an async API.
creds.refresh() makes a synchronous requests call to the token endpoint, on the event loop. Every other coroutine in the process stalls until it returns. For us that is live audio for every other call on the pod.
- No caching when the client was built without
credentials=. The resolved credentials are a local variable and are never stored on _api_client. Every connect() therefore runs google.auth.default() again and refreshes a fresh, token-less credentials object. The sync refresh runs on every connect, not once an hour.
The async REST path already handles both. _api_client._async_access_token() loads auth via asyncio.to_thread(load_auth, ...) under an async lock and caches it in self._credentials. async_get_token_from_credentials() refreshes via asyncio.to_thread(refresh_auth, ...), only when expired.
Repro
import asyncio, time
from google import genai
async def ticker(stop, worst):
while not stop.is_set():
t = time.perf_counter(); await asyncio.sleep(0.01)
worst[0] = max(worst[0], (time.perf_counter() - t - 0.01) * 1000)
async def main():
client = genai.Client() # Vertex via env, no credentials= passed
for i in range(3):
stop, worst = asyncio.Event(), [0.0]
tk = asyncio.create_task(ticker(stop, worst))
await asyncio.sleep(0.05) # let the ticker start before connect() blocks
async with client.aio.live.connect(
model="gemini-live-2.5-flash-native-audio",
config={"response_modalities": ["AUDIO"]},
):
pass
stop.set(); await tk
print(f"connect #{i+1}: max event-loop stall {worst[0]:.0f} ms")
await client.aio.aclose()
asyncio.run(main())
Output (Vertex, us-central1). I also counted service_account.Credentials.refresh calls:
connect #1: max event-loop stall 517 ms, token refreshes during connect: 1
connect #2: max event-loop stall 410 ms, token refreshes during connect: 1
connect #3: max event-loop stall 415 ms, token refreshes during connect: 1
Expected: auth resolved once per client, refresh only near expiry, and never on the event loop. Stalls should be a few ms.
Suggested fix
In AsyncLive.connect(), reuse the async REST path: await self._api_client._async_access_token(). That loads ADC off-loop, caches it on the client, and refreshes off-loop under the async auth lock. At minimum, store the resolved credentials on _api_client and wrap google.auth.default() and creds.refresh() in asyncio.to_thread.
Workaround
We build one genai.Client(credentials=creds) per process, in a thread. We keep creds FRESH by calling creds.refresh() via asyncio.to_thread whenever creds.token_state is not TokenState.FRESH. valid turns False at the same REFRESH_THRESHOLD, so connect() never takes the sync branch. With the same ticker, max stall per connect drops to 9–28 ms.
Environment
GOOGLE_GENAI_USE_VERTEXAI=true), service-account ADCWhat happens
On Vertex,
AsyncLive.connect()(google/genai/live.py, ~L1055-1069) runs this before it opens the websocket:Two problems:
creds.refresh()makes a synchronousrequestscall to the token endpoint, on the event loop. Every other coroutine in the process stalls until it returns. For us that is live audio for every other call on the pod.credentials=. The resolved credentials are a local variable and are never stored on_api_client. Everyconnect()therefore runsgoogle.auth.default()again and refreshes a fresh, token-less credentials object. The sync refresh runs on every connect, not once an hour.The async REST path already handles both.
_api_client._async_access_token()loads auth viaasyncio.to_thread(load_auth, ...)under an async lock and caches it inself._credentials.async_get_token_from_credentials()refreshes viaasyncio.to_thread(refresh_auth, ...), only when expired.Repro
Output (Vertex, us-central1). I also counted
service_account.Credentials.refreshcalls:Expected: auth resolved once per client, refresh only near expiry, and never on the event loop. Stalls should be a few ms.
Suggested fix
In
AsyncLive.connect(), reuse the async REST path:await self._api_client._async_access_token(). That loads ADC off-loop, caches it on the client, and refreshes off-loop under the async auth lock. At minimum, store the resolved credentials on_api_clientand wrapgoogle.auth.default()andcreds.refresh()inasyncio.to_thread.Workaround
We build one
genai.Client(credentials=creds)per process, in a thread. We keepcredsFRESH by callingcreds.refresh()viaasyncio.to_threadwhenevercreds.token_state is not TokenState.FRESH.validturns False at the sameREFRESH_THRESHOLD, soconnect()never takes the sync branch. With the same ticker, max stall per connect drops to 9–28 ms.