Mateo Wang f3904e2e65 feat(typesafe): support Jev 1.14 images, box questions, and long-context headers (#46596) ... * feat(typesafe): support Jev 1.14 images, box questions, and long-context headers * fix(cost): drop the typesafe/jev-1.14.0 entry main already prices * fix(typesafe): send images only with the images header and box questions only to models that answer them TypeSafe takes assets and input_image parts only when the request carries TypeSafe-Danger-Zone-Images: true, so without it they follow drop_params like any other provider that cannot take images. Box support now comes from a supports_box_questions cost-map flag set on jev-1.14.0 and jev-preview, so jev-1.13.0 and jev-latest refuse or drop a box question before the call. A malformed provider_specific_header answers 400 instead of 500. * fix(typesafe): allow null box confidence and validate asset references and base64 * fix(typesafe): gate box questions on the images header, drop unreadable assets under drop_params, forward opt-in headers on the pass-through --------- Backport of #46596 to rc/1.106.0 Cherry-picked from 3fec5075fa (main) Co-authored-by: devin-ai-integration[bot] <158243242+devin-ai-integration[bot]@users.noreply.github.com> Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>		2026-10-15 06:32:44 +00:00
..
__init__.py	feat(sdk): add litellm.systemone and trim litellm.decisions to the OpenAI shape (#45846)	2026-10-10 16:32:22 -07:00
test_main.py	feat(typesafe): support Jev 1.14 images, box questions, and long-context headers (#46596)	2026-10-15 06:32:44 +00:00