scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-09 22:31:41 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 87
litellm/tests/test_litellm/llms/gigachat
History
Exact
mateo-berri 91595780ec fix(gigachat): fold cached tokens back into prompt and total token counts 
GigaChat reports prompt_tokens and total_tokens after subtracting cached
tokens (the docs example is prompt_tokens=1, precached_prompt_tokens=37,
total_tokens=5, so the fields are disjoint, not a subset). Map to the
OpenAI convention by adding precached_prompt_tokens back onto prompt and
total while still surfacing it as prompt_tokens_details.cached_tokens.
2026-08-31 15:16:44 -07:00
..
chat fix(gigachat): fold cached tokens back into prompt and total token counts 2026-08-31 15:16:44 -07:00
embedding fix(gigachat): generic env-credential passthrough fallback plus type hardening 2026-08-29 22:08:54 -07:00
passthrough fix(lint): Partly fix basedpyright lint issues 2026-08-23 19:35:51 +00:00
__init__.py fix(tests): remove stale gigachat authenticator tests from old path, add utils tests 2026-08-23 11:15:06 +00:00
test_authenticator.py fix(passthrough): flush interrupted streams on client disconnect and reuse cached gigachat http clients 2026-08-30 13:36:51 -07:00
test_file_handler.py fix(passthrough): flush interrupted streams on client disconnect and reuse cached gigachat http clients 2026-08-30 13:36:51 -07:00
test_utils.py fix(gigachat): fold cached tokens back into prompt and total token counts 2026-08-31 15:16:44 -07:00