LocalAI/core/http
Richard Palethorpe 86b3bc9313
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>
2026-02-18 14:36:16 +01:00
..
endpoints fix(realtime): Better support for thinking models and setting model parameters (#8595) 2026-02-18 14:36:16 +01:00
middleware feat: add VoxCPM tts backend (#8109) 2026-01-28 14:44:04 +01:00
routes feat(musicgen): add ace-step and UI interface (#8396) 2026-02-05 12:04:53 +01:00
static feat(ui): left navbar, dark/light theme (#8594) 2026-02-18 00:14:39 +01:00
views feat(ui): left navbar, dark/light theme (#8594) 2026-02-18 00:14:39 +01:00
app.go chore: improve log levels verbosity (#8528) 2026-02-12 16:24:46 +01:00
app_test.go fix(realtime): Use user provided voice and allow pipeline models to have no backend (#8415) 2026-02-11 14:18:05 +01:00
explorer.go chore(refactor): move logging to common package based on slog (#7668) 2025-12-21 19:33:13 +01:00
http_suite_test.go feat(api): add support for open responses specification (#8063) 2026-01-17 22:11:47 +01:00
openresponses_test.go feat(api): add support for open responses specification (#8063) 2026-01-17 22:11:47 +01:00
render.go feat: migrate to echo and enable cancellation of non-streaming requests (#7270) 2025-11-14 22:57:53 +01:00