fix(realtime): Better support for thinking models and setting model parameters (#8595)
* fix(realtime): Wrap functions in OpenAI chat completions format Signed-off-by: Richard Palethorpe <io@richiejp.com> * feat(realtime): Set max tokens from session object Signed-off-by: Richard Palethorpe <io@richiejp.com> * fix(realtime): Find thinking start tag for thinking extraction Signed-off-by: Richard Palethorpe <io@richiejp.com> * fix(realtime): Don't send buffer cleared message when we automatically drop it Signed-off-by: Richard Palethorpe <io@richiejp.com> --------- Signed-off-by: Richard Palethorpe <io@richiejp.com>
R
Richard Palethorpe committed
86b3bc931395d91e51160dc5b29006ea8f866a88
Parent: 2fabdc0
Committed by GitHub <noreply@github.com>
on 2/18/2026, 1:36:16 PM