Hey team, My assistant keeps trying to call the get_free_slots function when checking availability, even though I’ve removed Functions and told it to only use go_high_level_calendar_check_availability_tool. Here’s the log snippet: { "name": "get_free_slots", "parameters": { "timeZone": "Europe/London", "startDate": 1696358400000, "endDate": 1701388800000 } } It always fails with: Error: API Error: 400 Request failed with status code 400 This happens instead of using my availability tool, and it blocks the assistant from booking. 👉 How can I fully disable or remove get_free_slots so it never gets exposed/called? Thanks!

I can help you fix this, the issue is that get_free_slots is still being exposed in your tool schema or cached, so the assistant defaults back to it. You’ll need to fully unregister it from your assistant’s tool config, not just remove it from usage. After that, re-deploy or refresh the assistant so it only sees go_high_level_calendar_check_availability_tool. Have you already tried clearing the schema and re-publishing? @toby

Hey @Vercel okay thank you! How do I do that? I can't see 'get_free_slots' in tools or anywhere in the setup

It’s likely still cached or hidden in your tool schema even if it’s not showing in the UI. You can clear it by updating the assistant’s schema or recreating the assistant without that function. I can walk you through the exact steps, let’s discuss it privately so I can assist you properly.

yeah sure thank you @Vercel

Alternatively you can poll /tool endpoint with GET and find the ID of the tool, then unattach it from your assistant configuration with an update like PATCH or PUT on the /assistant endpoint

Hey how can I do that. Are there any ways or places I can speak to somone to help? Happy to pay etc

Please provide your org id and assistant id you would like to modify

Hey Kyle thank you Org: 2e64e16f-71a2-4fc3-bd1e-1a2feaeecc7b Assistnant: e06b0506-1d9d-4156-ab00-43c8f7289ebc but it seems to happen on all assistants

@toby was this issue resolved for you? My team has been this issue for months. I've checked everything that has been advised, but the issue still occurs. I haven't been able to get any real support for the issue.

Hey @nomad318 kind of - i had to make a new organisation for each ghl sub account in vapi

We apologize for the delay in responses lately. We are in process of making some changes to our workflow in how we handle support requests. The good news is that we are starting to get back on track of having a 48 hour response time and we would like to start cleaning up anything old. With that being said, just wanted to check in with you to see if you have made any progress or changes to your project since support has last reached out.