Configurable Retries?!

[strawgate]

Im using Gemini and there don't appear to be retries on failed calls:

[INFO] 2025-05-17T11:22:23 mcp_agent.mcp-agent-as-yaml - Configuration loaded successfully. Ready to 
execute starting agent: Question Answer Orchestrator
[ERROR] 2025-05-17T11:22:25 mcp_agent.workflows.llm.augmented_llm_google.Question Answer Orchestrator - 
Error: 500 INTERNAL. {'error': {'code': 500, 'message': 'An internal error has occurred. Please retry or
report in https://developers.generativeai.google/guide/troubleshooting', 'status': 'INTERNAL'}}
[INFO] 2025-05-17T11:22:25 mcp_agent.mcp-agent-as-yaml - MCPAgent cleanup
{
  "data": {
    "progress_action": "Finished",
    "target": "mcp-agent-as-yaml",
    "agent_name": "mcp_application_loop"
  }
}
[mcp_agent.workflows.llm.augmented_llm_google.Question Answer Orchestrator] Error: 500 INTERNAL. {'error': {'code': 500, 'message': 'An internal error has occurred. Please retry or report in https://developers.generativeai.google/guide/troubleshooting', 'status': 'INTERNAL'}}

I see retry_policy in the code but that appears to be related to the temporal work going on?