# llmgw for VS Code

The models your llmgw gateway serves, in VS Code: in the chat's model
picker, in agent mode, and in any extension that asks VS Code for a language
model. Nothing goes anywhere but the gateway you connect it to.

## Connecting

1. **llmgw: Sign In** from the command palette. It opens your gateway's
   account page; sign in there and choose **Make a key and the
   configuration** with *VS Code* as the tool. The page hands the key back to
   VS Code.
2. Or **llmgw: Enter API Key** and paste a key from that page.

The gateway's address is the `llmgw.gatewayUrl` setting. An extension
downloaded from a gateway has that gateway's address in it already.

The key is kept in VS Code's secret storage. **llmgw: Sign Out** forgets it;
revoke it on the account page to stop it working.

## Which models

Every chat model the key may use. Agent mode acts only through tool calls,
so it needs a model the gateway's catalog says makes them; set
`llmgw.showModelsWithoutTools` to `false` to see only those.

Completion as you type is not part of what VS Code lets a model provider
offer; for that, use an extension such as Continue against the same gateway.