RoundSun
03/25/2025, 6:42 PMVapi Support Bot
03/25/2025, 6:44 PMVapi Support Bot
03/25/2025, 6:44 PMassistantOverrides.maxDurationSeconds
or adjusting numWordsToInterruptAssistant
as suggested in [Discord discussions](https://discord.com/channels/1211482211119796234/1211483291191083018/threads/1335807780287676456).
4. **Enable Detailed Logging**: While you mentioned logs don't provide insights, make sure you're checking for error messages or warnings in the organization's VAPI logs. You can also access webhook delivery logs through the VAPI dashboard.
5. **Gather Specific Information**: If you need to contact support, collect the call ID, timestamp, expected response, and actual response to help track down the issue.
6. **Check for Model Switching**: Review call logs to see if the model switches during the call, which could cause the assistant to lose context.
Would you like me to elaborate on any of these debugging steps or potential causes? Or perhaps you could share more details about your prompt script structure?
Sources:
- [Discord discussions](https://discord.com/channels/1211482211119796234/1211483291191083018/threads/1343612796717371393)
- [User reports](https://discord.com/channels/1211482211119796234/1211483291191083018/threads/1340523490662416494)
- [Documentation](https://discord.com/channels/1211482211119796234/1316042862630146058)
- [Discord discussions](https://discord.com/channels/1211482211119796234/1211483291191083018/threads/1335807780287676456)RoundSun
03/25/2025, 6:54 PMShubham Bajaj
03/26/2025, 10:58 PM