@chia5966
I'm sorry to hear that you're experiencing issues with the calls hanging up and encountering error messages. It seems like there might be multiple issues at play here, including an unknown error and specific pipeline errors related to the Anthropic LLM.
For the pipeline errors, it's possible that there is an issue with the integration of the LLM model you're trying to use. This could be due to a temporary service disruption or a configuration issue. Since you mentioned that functions were not working over the weekend but then started working again, it could also be an intermittent problem.
Regarding the Claude 3.5 Sonnet errors, if you're experiencing issues specifically with this model, it might be related to the pipeline-no-available-llm-model context, indicating that the LLM was not available to process the request.
To assist you further and resolve these issues, I would need to gather more details about the specific problems you're facing with the calls and the functions you're trying to use. Could you please provide more information about the steps you're taking and the exact errors you're seeing? This will help me understand the situation better and provide you with the appropriate support.
In the meantime, if you have any provider keys or subscription details, please ensure they are correctly configured and that you haven't exceeded any limits or quotas, as suggested by the pipeline-error-first-message-failed context.
If you need immediate assistance or if the issue persists, please ask support for more info on this.