NotificationsYou must be signed in to change notification settings
Fork1k
Star11k

Bugfix: avoid race condition when refreshing google token#2100

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to ourterms of service andprivacy statement. We’ll occasionally send you account related emails.

Already on GitHub?Sign in to your account

Jump to bottom

Merged

Kludex merged 2 commits intopydantic:mainfromJadHADDAD92:gemini_token

Jul 15, 2025

Merged

Bugfix: avoid race condition when refreshing google token#2100

Kludex merged 2 commits intopydantic:mainfromJadHADDAD92:gemini_token

Jul 15, 2025

Conversation

Copy link

Contributor

JadHADDAD92 commentedJun 30, 2025

Hello,
I have been having an issue with the refresh token when launching multiple Gemini agents concurrently.
Here is a minimal reproducible code:

Class handling agent

classInformationExtractionAgent:def__init__(self):self.model=GeminiModel("gemini-2.5-pro",provider=GoogleVertexProvider(service_account_file=os.path.join("shared","config","gemini.json"),region="europe-west1",            ),        )self.settings=GeminiModelSettings(gemini_thinking_config={"thinking_budget":128,"include_thoughts":True}        )self.agent=Agent(model=self.model,model_settings=self.settings,output_type=DocumentExtractionResult,system_prompt="..."        )asyncdefextract_information(...)->AgentRunResult[DocumentExtractionResult]:result=awaitself.agent.run("...")returnresult

This class is called and used from a coroutine

asyncdefextraction_process(...):information_extraction_agent=InformationExtractionAgent()# [...]extraction_result=awaitinformation_extraction_agent.extract_information(...)# [...]

and this coroutine is called concurrently in a Semaphore

asyncrun_extraction_job(tasks_ids):semaphore=Semaphore(10)# [...]asyncdefsemaphore_execute_task(task_id:int):asyncwithsemaphore:awaitextraction_process(task_id)# [...]awaitasyncio.gather(*[semaphore_execute_task(task_id)fortask_idintask_ids])

I would randomly get this error, not consistently, even though all the instances have the service_account_file configured toshared/config/gemini.json, seems like a race condition:

backend-1  |   File "/usr/local/lib/python3.11/site-packages/httpx/_client.py", line 1654, in _send_handling_authbackend-1  |     request = await auth_flow.__anext__()backend-1  |               ^^^^^^^^^^^^^^^^^^^^^^^^^^^backend-1  |   File "/usr/local/lib/python3.11/site-packages/pydantic_ai/providers/google_vertex.py", line 134, in async_auth_flowbackend-1  |     await self._refresh_token()backend-1  |   File "/usr/local/lib/python3.11/site-packages/pydantic_ai/providers/google_vertex.py", line 169, in _refresh_tokenbackend-1  |     assert isinstance(self.credentials.token, str), f'Expected token to be a string, got {self.credentials.token}'  # type: ignore[reportUnknownMemberType]backend-1  |            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^backend-1  | AssertionError: Expected token to be a string, got None

with the help of Mert Sırakaya, here is a patch for this error, I have tried running the test many times after the patch, I don't have any errors, and then tried again without the patch and I occasionally got the error again.

For the typing lint I have putignore[reportUnknownMemberType] comments because I didn't know what else to do, I'm open to better suggestions

Bugfix: avoid race condition when refreshing google token

17bf7f1

Copy link

Contributor

DouweM commentedJul 1, 2025

@JadHADDAD92 Thanks Jad. This look like the same issue as#1440. There, my colleague Marcelo this should be solved with the newGoogleModel andGoogleProvider(vertexai=True) you can use instead ofGeminiModel andGoogleVertexProvider as in the example here:https://ai.pydantic.dev/models/google/#vertex-ai-enterprisecloud. Can you see if that works?

Note that this PR may still make sense, but I want to verify the new classes also work for you.

DouweM self-assigned this

Jul 1, 2025

Copy link

ContributorAuthor

JadHADDAD92 commentedJul 1, 2025

I have triedGoogleModel with the following configs

classInformationExtractionAgent:def__init__(self):credentials=service_account.Credentials.from_service_account_file(os.path.join("shared","config","gemini.json"),scopes=["https://www.googleapis.com/auth/cloud-platform"],        )self.model=GoogleModel("gemini-2.5-pro",provider=GoogleProvider(credentials=credentials,location="europe-west1",            ),        )self.settings=GoogleModelSettings(google_thinking_config={"thinking_budget":128,"include_thoughts":True}        )