Commit graph

5 commits

Author SHA1 Message Date
Ettore Di Giacinto
6d9d77d590
fix(reasoning): accumulate and strip reasoning tags from autoparser results (#9227)
fix(reasoning): acccumulate and strip reasoning tags from autoparser results

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2026-04-04 18:15:32 +02:00
Ettore Di Giacinto
9f8821bba8
feat(gemma4): add thinking support (#9221)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2026-04-04 12:11:38 +02:00
Ettore Di Giacinto
ee96e5e08d
chore: refactor endpoints to use same inferencing path, add automatic retrial mechanism in case of errors (#9029)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2026-03-16 21:31:02 +01:00
Ettore Di Giacinto
c491c6ca90
feat(openresponses): Support reasoning blocks (#8133)
* feat(openresponses): support reasoning blocks

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* allow to disable reasoning, refactor common logic

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Add option to only strip reasoning

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Add configurations for custom reasoning tokens

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2026-01-21 00:11:45 +01:00
Ettore Di Giacinto
34e054f607
fix(reasoning): support models with reasoning without starting thinking tag (#8132)
* chore: extract reasoning to its own package

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* make sure we detect thinking tokens from template

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Allow to override via config, add tests

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2026-01-20 21:07:59 +01:00