Timeout configuration not respected by ChatGoogleGenerativeAI

[davidvesp]

If you execute the following code:

from langchain_google_genai import GoogleGenerativeAI
llm = GoogleGenerativeAI(model="gemini-2.0-flash", temperature=0.2, timeout=1, max_retries=1)
print(llm.invoke("Tell me a story in 1000 words."))

It fails with the expected output:

DeadlineExceeded                          

But if you use the following code:

from langchain_google_genai import ChatGoogleGenerativeAI
llm = ChatGoogleGenerativeAI(model="gemini-2.0-flash", temperature=0.2, timeout=1, max_retries=0)
print(llm.invoke("Tell me a story in 1000 words."))

It ends ok (we want to set the timeout to fail fast).

I tried using the native Google library and it respects the timeout config:

import os
import google.generativeai as genai

genai.configure(api_key="")

# Create the model
generation_config = {
  "temperature": 0.7,
  "top_p": 0.95,
  "top_k": 64,
  "max_output_tokens": 65536,
  "response_mime_type": "text/plain",
}

model = genai.GenerativeModel(
  model_name="gemini-2.0-flash",
  generation_config=generation_config,
)

chat_session = model.start_chat(
  history=[
  ]
)

response = chat_session.send_message("tell me a story in 1000 words", request_options={"timeout": 3})

print(response.text)

Output:

DeadlineExceeded