Now I’m also having the following error for GEMINI:
got status: RESOURCE_EXHAUSTED. {“error”:{“code”:429,“message”:“Resource exhausted. Please try again later. Please refer to https://cloud.google.com/vertex-ai/generative-ai/docs/error-code-429 for more details.”,“status”:“RESOURCE_EXHAUSTED”}}
I think we are having a bug with the LLMs. If I use the same model (like GEMINI FLASH) in one workflow, calls a RUN WORKFLOW block, and run the same LLM model in it, it will return a fail… Would you please confirm?
I am currently attempting to replicate this error, but it looks like the Max Reasoning Size setting may have included characters other than numbers. Could you try adjusting the setting with the slider, publish the Agent, and try again?
Thanks for flagging this, we’re looking into it
You can use the same model across workflows. The issue seems to be specific to Gemini models with thinking enabled.
I had the same impression. I’m not able to delete the reasoning size after I first include a number. So, I created another workflow and replicated the other one… Is it a bug in max reasoning size?