RetryHttpOptions ignored for client.aio.models.generate_content_stream

[VMinB12]

client.aio.models.generate_content_stream ignores the HttpOptions.RetryHTTPOptions and does no retry whatsoever. Note that the sync client.models.generate_content_stream does properly handle retry options.

Environment details

• Programming language: Python
• OS: MacOS
• Package version: 1.62.0

Steps to reproduce

Here is a minimum reproducible example (Assuming you hit the 429 rate limit as I am getting currently).

import logging

from google.genai import Client, types

logging.basicConfig(level=logging.DEBUG)
logger = logging.getLogger(__name__)
client = Client()




async def main():
    logger.info(f"SYNC TEST: Starting test of retry options with generate_content_stream")
    try:
        for event in client.models.generate_content_stream(
            model="gemini-2.0-flash",
            contents=types.Content(parts=[types.Part(text="hello")], role="user"),
            config=types.GenerateContentConfig(
                max_output_tokens=10,
                temperature=0.2,
                http_options=types.HttpOptions(
                    retry_options=types.HttpRetryOptions(
                        attempts=3,
                        initial_delay=1,
                        max_delay=2,
                    )
                )
            ),
        ):
            print(event)
    except Exception:
        pass

    logger.info("-"*80 + "\n\n")
    logger.info(f"ASYNC TEST: Starting test of retry options with generate_content_stream")
    try:
        async for event in await client.aio.models.generate_content_stream(
            model="gemini-2.0-flash",
            contents=types.Content(parts=[types.Part(text="hello")], role="user"),
            config=types.GenerateContentConfig(
                max_output_tokens=10,
                temperature=0.2,
                http_options=types.HttpOptions(
                    retry_options=types.HttpRetryOptions(
                        attempts=3,
                        initial_delay=1,
                        max_delay=2,
                    )
                )
            ),
        ):
            print(event)
    except Exception:
        pass

if __name__ == "__main__":
    import asyncio
    asyncio.run(main())

Here are the output logs:

DEBUG:asyncio:Using selector: KqueueSelector
INFO:__main__:SYNC TEST: Starting test of retry options with generate_content_stream
INFO:google_genai.models:AFC is enabled with max remote calls: 10.
DEBUG:httpcore.connection:connect_tcp.started host='generativelanguage.googleapis.com' port=443 local_address=None timeout=None socket_options=None
DEBUG:httpcore.connection:connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x10587cdd0>
DEBUG:httpcore.connection:start_tls.started ssl_context=<ssl.SSLContext object at 0x100990a50> server_hostname='generativelanguage.googleapis.com' timeout=None
DEBUG:httpcore.connection:start_tls.complete return_value=<httpcore._backends.sync.SyncStream object at 0x103a24ec0>
DEBUG:httpcore.http11:send_request_headers.started request=<Request [b'POST']>
DEBUG:httpcore.http11:send_request_headers.complete
DEBUG:httpcore.http11:send_request_body.started request=<Request [b'POST']>
DEBUG:httpcore.http11:send_request_body.complete
DEBUG:httpcore.http11:receive_response_headers.started request=<Request [b'POST']>
DEBUG:httpcore.http11:receive_response_headers.complete return_value=(b'HTTP/1.1', 429, b'Too Many Requests', [(b'Vary', b'Origin'), (b'Vary', b'X-Origin'), (b'Vary', b'Referer'), (b'Content-Type', b'text/event-stream'), (b'Date', b'Mon, 09 Feb 2026 08:57:12 GMT'), (b'Server', b'scaffolding on HTTPServer2'), (b'Content-Length', b'2276'), (b'X-XSS-Protection', b'0'), (b'X-Frame-Options', b'SAMEORIGIN'), (b'X-Content-Type-Options', b'nosniff'), (b'Server-Timing', b'gfet4t7; dur=48'), (b'Alt-Svc', b'h3=":443"; ma=2592000,h3-29=":443"; ma=2592000')])
INFO:httpx:HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-2.0-flash:streamGenerateContent?alt=sse "HTTP/1.1 429 Too Many Requests"
DEBUG:httpcore.http11:receive_response_body.started request=<Request [b'POST']>
DEBUG:httpcore.http11:receive_response_body.complete
DEBUG:httpcore.http11:response_closed.started
DEBUG:httpcore.http11:response_closed.complete
INFO:google_genai._api_client:Retrying google.genai._api_client.BaseApiClient._request_once in 1.4916958010268493 seconds as it raised ClientError: 429 RESOURCE_EXHAUSTED. {'error': {'code': 429, 'message': 'You exceeded your current quota, please check your plan and billing details. For more information on this error, head to: https://ai.google.dev/gemini-api/docs/rate-limits. To monitor your current usage, head to: https://ai.dev/rate-limit. \n* Quota exceeded for metric: generativelanguage.googleapis.com/generate_content_free_tier_requests, limit: 0, model: gemini-2.0-flash\n* Quota exceeded for metric: generativelanguage.googleapis.com/generate_content_free_tier_requests, limit: 0, model: gemini-2.0-flash\n* Quota exceeded for metric: generativelanguage.googleapis.com/generate_content_free_tier_input_token_count, limit: 0, model: gemini-2.0-flash\nPlease retry in 47.744895045s.', 'status': 'RESOURCE_EXHAUSTED', 'details': [{'@type': 'type.googleapis.com/google.rpc.Help', 'links': [{'description': 'Learn more about Gemini API quotas', 'url': 'https://ai.google.dev/gemini-api/docs/rate-limits'}]}, {'@type': 'type.googleapis.com/google.rpc.QuotaFailure', 'violations': [{'quotaMetric': 'generativelanguage.googleapis.com/generate_content_free_tier_requests', 'quotaId': 'GenerateRequestsPerDayPerProjectPerModel-FreeTier', 'quotaDimensions': {'location': 'global', 'model': 'gemini-2.0-flash'}}, {'quotaMetric': 'generativelanguage.googleapis.com/generate_content_free_tier_requests', 'quotaId': 'GenerateRequestsPerMinutePerProjectPerModel-FreeTier', 'quotaDimensions': {'location': 'global', 'model': 'gemini-2.0-flash'}}, {'quotaMetric': 'generativelanguage.googleapis.com/generate_content_free_tier_input_token_count', 'quotaId': 'GenerateContentInputTokensPerModelPerMinute-FreeTier', 'quotaDimensions': {'location': 'global', 'model': 'gemini-2.0-flash'}}]}, {'@type': 'type.googleapis.com/google.rpc.RetryInfo', 'retryDelay': '47s'}]}}.
DEBUG:httpcore.http11:send_request_headers.started request=<Request [b'POST']>
DEBUG:httpcore.http11:send_request_headers.complete
DEBUG:httpcore.http11:send_request_body.started request=<Request [b'POST']>
DEBUG:httpcore.http11:send_request_body.complete
DEBUG:httpcore.http11:receive_response_headers.started request=<Request [b'POST']>
DEBUG:httpcore.http11:receive_response_headers.complete return_value=(b'HTTP/1.1', 429, b'Too Many Requests', [(b'Vary', b'Origin'), (b'Vary', b'X-Origin'), (b'Vary', b'Referer'), (b'Content-Type', b'text/event-stream'), (b'Date', b'Mon, 09 Feb 2026 08:57:13 GMT'), (b'Server', b'scaffolding on HTTPServer2'), (b'Content-Length', b'2276'), (b'X-XSS-Protection', b'0'), (b'X-Frame-Options', b'SAMEORIGIN'), (b'X-Content-Type-Options', b'nosniff'), (b'Server-Timing', b'gfet4t7; dur=28'), (b'Alt-Svc', b'h3=":443"; ma=2592000,h3-29=":443"; ma=2592000')])
INFO:httpx:HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-2.0-flash:streamGenerateContent?alt=sse "HTTP/1.1 429 Too Many Requests"
DEBUG:httpcore.http11:receive_response_body.started request=<Request [b'POST']>
DEBUG:httpcore.http11:receive_response_body.complete
DEBUG:httpcore.http11:response_closed.started
DEBUG:httpcore.http11:response_closed.complete
INFO:google_genai._api_client:Retrying google.genai._api_client.BaseApiClient._request_once in 2.0 seconds as it raised ClientError: 429 RESOURCE_EXHAUSTED. {'error': {'code': 429, 'message': 'You exceeded your current quota, please check your plan and billing details. For more information on this error, head to: https://ai.google.dev/gemini-api/docs/rate-limits. To monitor your current usage, head to: https://ai.dev/rate-limit. \n* Quota exceeded for metric: generativelanguage.googleapis.com/generate_content_free_tier_requests, limit: 0, model: gemini-2.0-flash\n* Quota exceeded for metric: generativelanguage.googleapis.com/generate_content_free_tier_requests, limit: 0, model: gemini-2.0-flash\n* Quota exceeded for metric: generativelanguage.googleapis.com/generate_content_free_tier_input_token_count, limit: 0, model: gemini-2.0-flash\nPlease retry in 46.160710101s.', 'status': 'RESOURCE_EXHAUSTED', 'details': [{'@type': 'type.googleapis.com/google.rpc.Help', 'links': [{'description': 'Learn more about Gemini API quotas', 'url': 'https://ai.google.dev/gemini-api/docs/rate-limits'}]}, {'@type': 'type.googleapis.com/google.rpc.QuotaFailure', 'violations': [{'quotaMetric': 'generativelanguage.googleapis.com/generate_content_free_tier_requests', 'quotaId': 'GenerateRequestsPerDayPerProjectPerModel-FreeTier', 'quotaDimensions': {'location': 'global', 'model': 'gemini-2.0-flash'}}, {'quotaMetric': 'generativelanguage.googleapis.com/generate_content_free_tier_requests', 'quotaId': 'GenerateRequestsPerMinutePerProjectPerModel-FreeTier', 'quotaDimensions': {'location': 'global', 'model': 'gemini-2.0-flash'}}, {'quotaMetric': 'generativelanguage.googleapis.com/generate_content_free_tier_input_token_count', 'quotaId': 'GenerateContentInputTokensPerModelPerMinute-FreeTier', 'quotaDimensions': {'model': 'gemini-2.0-flash', 'location': 'global'}}]}, {'@type': 'type.googleapis.com/google.rpc.RetryInfo', 'retryDelay': '46s'}]}}.
DEBUG:httpcore.http11:send_request_headers.started request=<Request [b'POST']>
DEBUG:httpcore.http11:send_request_headers.complete
DEBUG:httpcore.http11:send_request_body.started request=<Request [b'POST']>
DEBUG:httpcore.http11:send_request_body.complete
DEBUG:httpcore.http11:receive_response_headers.started request=<Request [b'POST']>
DEBUG:httpcore.http11:receive_response_headers.complete return_value=(b'HTTP/1.1', 429, b'Too Many Requests', [(b'Vary', b'Origin'), (b'Vary', b'X-Origin'), (b'Vary', b'Referer'), (b'Content-Type', b'text/event-stream'), (b'Date', b'Mon, 09 Feb 2026 08:57:15 GMT'), (b'Server', b'scaffolding on HTTPServer2'), (b'Content-Length', b'2275'), (b'X-XSS-Protection', b'0'), (b'X-Frame-Options', b'SAMEORIGIN'), (b'X-Content-Type-Options', b'nosniff'), (b'Server-Timing', b'gfet4t7; dur=30'), (b'Alt-Svc', b'h3=":443"; ma=2592000,h3-29=":443"; ma=2592000')])
INFO:httpx:HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-2.0-flash:streamGenerateContent?alt=sse "HTTP/1.1 429 Too Many Requests"
DEBUG:httpcore.http11:receive_response_body.started request=<Request [b'POST']>
DEBUG:httpcore.http11:receive_response_body.complete
DEBUG:httpcore.http11:response_closed.started
DEBUG:httpcore.http11:response_closed.complete
INFO:__main__:--------------------------------------------------------------------------------


INFO:__main__:ASYNC TEST: Starting test of retry options with generate_content_stream
INFO:google_genai.models:AFC is enabled with max remote calls: 10.
DEBUG:httpcore.connection:connect_tcp.started host='generativelanguage.googleapis.com' port=443 local_address=None timeout=None socket_options=None
DEBUG:httpcore.connection:connect_tcp.complete return_value=<httpcore._backends.anyio.AnyIOStream object at 0x10587e690>
DEBUG:httpcore.connection:start_tls.started ssl_context=<ssl.SSLContext object at 0x100990a50> server_hostname='generativelanguage.googleapis.com' timeout=None
DEBUG:httpcore.connection:start_tls.complete return_value=<httpcore._backends.anyio.AnyIOStream object at 0x1052fa510>
DEBUG:httpcore.http11:send_request_headers.started request=<Request [b'POST']>
DEBUG:httpcore.http11:send_request_headers.complete
DEBUG:httpcore.http11:send_request_body.started request=<Request [b'POST']>
DEBUG:httpcore.http11:send_request_body.complete
DEBUG:httpcore.http11:receive_response_headers.started request=<Request [b'POST']>
DEBUG:httpcore.http11:receive_response_headers.complete return_value=(b'HTTP/1.1', 429, b'Too Many Requests', [(b'Vary', b'Origin'), (b'Vary', b'X-Origin'), (b'Vary', b'Referer'), (b'Content-Type', b'text/event-stream'), (b'Date', b'Mon, 09 Feb 2026 08:57:16 GMT'), (b'Server', b'scaffolding on HTTPServer2'), (b'Content-Length', b'2276'), (b'X-XSS-Protection', b'0'), (b'X-Frame-Options', b'SAMEORIGIN'), (b'X-Content-Type-Options', b'nosniff'), (b'Server-Timing', b'gfet4t7; dur=29'), (b'Alt-Svc', b'h3=":443"; ma=2592000,h3-29=":443"; ma=2592000')])
INFO:httpx:HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-2.0-flash:streamGenerateContent?alt=sse "HTTP/1.1 429 Too Many Requests"
DEBUG:httpcore.http11:receive_response_body.started request=<Request [b'POST']>
DEBUG:httpcore.http11:receive_response_body.complete
DEBUG:httpcore.http11:response_closed.started
DEBUG:httpcore.http11:response_closed.complete
DEBUG:httpcore.connection:close.started
DEBUG:httpcore.connection:close.complete

Note that we see 3 attempts for the sync version, but only 1 attempt for the async version.

[miguelmanlyx]

@VMinB12
Looks like a Streaming issue. Have you run npx ai-patch doctor to sanity-check stalls/partial output and common SSE buffering pitfalls?