Vapi is the Voice AI platform for developers.

Vapi AI

I'm getting a frequent error that is casuing my call to end: pipeline-error-anthropic-llm-failed. In the logs, I get: 

Model request failed (attempt #2, reason: (messages.14: Did not find 1 `tool_result` block(s) at the beginning of this message. Messages following `tool_use` blocks must begin with a matching number of `tool_result` blocks.)). 

Then the call ends.

<@1181432301335367680>
I'm sorry to hear that you're experiencing issues with your calls. It seems like there might be a problem with how the tool results are being handled in the pipeline. To address this, we should ensure that the tool use and tool result blocks are correctly formatted and sequenced.

If you're using any custom scripts or integrations, please double-check that the responses from tool uses are being processed correctly and that the `tool_result` blocks are present at the beginning of the messages following `tool_use` blocks as expected.

If the problem persists or you're unsure about how to proceed, please reach out to support for more detailed assistance. They can provide you with specific guidance tailored to your setup and help resolve the issue.

You can continue this conversation by mentioning me in the message.

Got it. Tagging <@&1231325148079194222> for additional help.

I was about to put this into production with our client, so need support asap please

if it helps, my anthropic account logs contain this error: {
  "client_error": true,
  "code": 499,
  "detail": "Client disconnected"
}

<@&1231325148079194222> can I get some feedback on this please? It's rather urgent as this is currently with my client for testing

<@1181432301335367680> please try now the issue has been resolved?

thanks - we actually switched over to open ai model in order to avoid the issue. I will retest with Claude when i get the chance

<@865531204849500190> looks like it is not yet resolved

<@1181432301335367680> could you share the recent call ID so I can take a look?