Support gpt 3.5 turbo 16k model (#424)

`TokenLimits` is only the place needed to be modified. Have set the
token limits accordingly. Closes #406
<!-- This is an auto-generated comment: release notes by OSS CodeRabbit
-->
### Summary by CodeRabbit

**New Feature:**
- Added support for the "gpt-3.5-turbo-16k" model in the `TokenLimits`
class.
- Set the `maxTokens` limit to 16300 and the `responseTokens` limit to
3000 for the new model.

> 🎉 With tokens aplenty, we set the stage,
> For the "gpt-3.5-turbo-16k" to engage.
> More power, more wisdom, in every page,
> A new chapter begins, let's turn the page! 🚀
<!-- end of auto-generated comment: release notes by OSS CodeRabbit -->

Author: HyunggyuJang

src/limits.ts

@@ -9,6 +9,9 @@ export class TokenLimits {
     if (model === 'gpt-4-32k') {
       this.maxTokens = 32600
       this.responseTokens = 4000
+    } else if (model === 'gpt-3.5-turbo-16k') {
+      this.maxTokens = 16300
+      this.responseTokens = 3000
     } else if (model === 'gpt-4') {
       this.maxTokens = 8000
       this.responseTokens = 2000