search

twinnydotdev / twinny

The most no-nonsense, locally or API-hosted AI code completion plugin for Visual Studio Code - like GitHub Copilot but completely free and 100% private.
https://twinny.dev
MIT License
2.93k stars 154 forks source link

COMPLETION_TIMEOUT = 20000 is causing chat generation to halt early #171

Closed Yazorp closed 7 months ago

Yazorp commented 7 months ago

Describe the bug The current hard coded setting of export const COMPLETION_TIMEOUT = 20000 // 20 seconds is causing chat generations such as "Explain" to stop early even though the token limit hasn't been reached.

Suggest either making this at least 2 minutes at 120000 or adding a configurable settings entry.

rjmacarthy commented 7 months ago

Hmm, it's meant to be a timeout if the request is taking too long..I guess I can just remove it instead if it's causing issues. I remove it in 3.7.15 as it was logic from the old stream code and probably not needed.