Experiencing an issue intermittently, where the assistant just stops responding. This usually happens just before it should be making its final tool call. The tool call never hits my server, and the assistant stops responding entirely. There are no errors in the Call Log as far as I can tell, and I can't seem to determine what is causing this to happen only some of the time. is anyone able to help with this? most recent call id where i have experienced the issue: bc724e34-bf32-4d93-b074-a5b4efb111fe also happened with this one: 846f9a6e-e0c3-414a-a81f-e490fce00ac3

Since there are no errors in your Call Log and the issue is intermittent, the best next step is to contact Vapi support with your

call_id

and account email address. This allows the support team to investigate deeper using internal logs and diagnostics that aren't available in the dashboard. You can reference the [Vapi Call Ended Reasons documentation](https://docs.vapi.ai/calls/call-ended-reason) for more details, but direct support is recommended for unexplained or intermittent issues. Source: - [Vapi Call Ended Reasons documentation](https://docs.vapi.ai/calls/call-ended-reason)

call ids are above, i can provide my email in a private DM if needed

{
      "role": "tool_calls",
      "time": 1747773870457,
      "message": "",
      "toolCalls": [
        {
          "id": "call_f31ltoIhAeczNixAc9mjZYfr",
          "type": "function",
          "function": {
            "name": "place_order",
            "arguments": "{}"
          }
        }
      ],
      "secondsFromStart": 229.616
    },
    {
      "name": "place_order",
      "role": "tool_call_result",
      "time": 1747773870842,
      "result": "No result returned.",
      "toolCallId": "call_f31ltoIhAeczNixAc9mjZYfr",
      "secondsFromStart": 230.001
    },

It appears that your place order function didn't include any arguments and I'm not sure if that was intentional.

that happened after the assistant stopped responding. the tool does have arguments. my current theory is that this has something to do with max tokens. and the tool call exceeded that. would that not show up in the logs though ?

The assistant's delayed response is due to end pointing, which determines the duration to wait before recognizing the user has finished speaking. - End Pointing Plan Configuration: You need to adjust the Smart End Pointing plan provider to livekit and update the wait function within the Start Speaking Plan for English Transcription. - Wait Function Optimization: Iterative testing with potential users is necessary to determine the optimal wait function values, as suggested values may not be suitable for all scenarios.

startSpeakingPlan": {
  "waitSeconds": 0.4,
  "smartEndpointingPlan": {
          "provider": "livekit",
          "waitFunction": "2000 / (1 + exp(-10 * (x - 0.5)))"
        }
}