LLM Latency Spikes (3-5 min) during Error Handling in Google ADK

[fedorovychh]

When a tool wrote with Google ADK returns a "failed operation" response, the LLM experiences an abnormal delay (3–5 minutes) before attempting to fix parameters or respond. This "infinite thinking" loop occurs specifically after an error is injected into the conversation context.

What are the most effective strategies to prevent the LLM from getting stuck in a "reasoning loop" after a tool failure—is it better to strip the error response to a bare code, or is there a specific ADK configuration to bypass this latency?